INDEX

Explanations

character names and technical terms, potentially related to specific subjects like botany or sports

oai_token-act-pair · gpt-3.5-turbo

specific character sequences and names associated with particular entities, likely within a narrative or thematic context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

heim

-0.77

liga

-0.69

opa

-0.69

lov

-0.67

park

-0.65

 Braun

-0.64

urious

-0.63

borg

-0.63

DL

-0.63

isd

-0.62

POSITIVE LOGITS

rees

0.83

ieves

0.80

uctor

0.75

reen

0.73

aves

0.72

anooga

0.72

\\\\\\\\

0.71

reet

0.70

entials

0.70

================================================================

0.67

Activations Density 0.042%

character names and technical terms, potentially related to specific subjects like botany or sports

specific character sequences and names associated with particular entities, likely within a narrative or thematic context

No Comments

No Known Activations