INDEX

Explanations

phrases related to specific actions or associations with individuals or entities

oai_token-act-pair · gpt-3.5-turbo

phrases indicating various forms of involvement or participation in activities or events

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

Float

-0.76

auld

-0.75

sell

-0.72

imb

-0.72

geon

-0.70

geons

-0.69

\\\\\\\\

-0.67

 Balanced

-0.66

 passage

-0.64

umb

-0.62

POSITIVE LOGITS

enza

0.88

 involvement

0.87

ateral

0.75

itaire

0.70

ioned

0.68

iveness

0.67

 role

0.66

 destro

0.65

cius

0.65

 manual

0.65

Activations Density 0.027%

phrases related to specific actions or associations with individuals or entities

phrases indicating various forms of involvement or participation in activities or events

No Comments

No Known Activations