INDEX

Explanations

mentions of legal and political actions or decisions

oai_token-act-pair · gpt-3.5-turbo

instances of numerical values or ratings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

Ĥ

-0.90

©

-0.85

poon

-0.78

¡

-0.73

¥µ

-0.72

¬

-0.70

baugh

-0.69

Ĥ¬

-0.68

Ĭ

-0.67

ī

-0.67

POSITIVE LOGITS

FILE

1.22

Fresh

0.76

Returns

0.71

ÂłÂłÂłÂłÂłÂłÂłÂł

0.70

Actor

0.69

Shell

0.69

IJ

0.69

âĵĺ

0.68

Credit

0.67

article

0.67

Activations Density 0.076%

mentions of legal and political actions or decisions

instances of numerical values or ratings

No Comments

No Known Activations