INDEX

Explanations

terms related to legal or policy-related concepts

oai_token-act-pair · gpt-3.5-turbo

words related to social issues and policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

terness

-0.87

erity

-0.83

inness

-0.74

zzi

-0.72

 Nicotine

-0.69

External

-0.69

tyard

-0.69

esthetic

-0.68

nen

-0.67

 CrossRef

-0.66

POSITIVE LOGITS

 boarding

0.82

 queen

0.80

 killers

0.79

 commissions

0.79

 programming

0.76

 camps

0.75

 eligibility

0.72

 laboratories

0.71

 outfits

0.71

 labs

0.70

Activations Density 0.435%

terms related to legal or policy-related concepts

words related to social issues and policies

No Comments

No Known Activations