INDEX

Explanations

mentions of specific names or entities, potentially related to legal or medical contexts

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names associated with individuals or entities

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

emetery

-0.72

 Sacrament

-0.71

 Soup

-0.68

ressed

-0.67

ressing

-0.66

ovember

-0.66

ividual

-0.65

resso

-0.65

ental

-0.64

 ceilings

-0.63

POSITIVE LOGITS

sey

0.85

pin

0.77

aye

0.77

board

0.76

ged

0.74

ãĥīãĥ©

0.73

chal

0.73

lessly

0.73

kus

0.72

wash

0.72

Activations Density 0.035%

mentions of specific names or entities, potentially related to legal or medical contexts

proper nouns and names associated with individuals or entities

No Comments

No Known Activations