INDEX

Explanations

reviews

oai_token-act-pair · gpt-3.5-turbo

terms related to reviews and ratings

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

chest

-0.73

bodied

-0.68

pox

-0.68

fw

-0.68

llular

-0.67

nown

-0.67

iak

-0.67

 Flore

-0.66

unin

-0.65

pots

-0.64

POSITIVE LOGITS

Reviewed

0.99

 Reviews

0.95

 reviews

0.89

 reviewer

0.84

Review

0.83

 review

0.78

 embargo

0.76

 reviewers

0.75

 essays

0.75

rating

0.75

Activations Density 0.035%

reviews

terms related to reviews and ratings

No Comments

No Known Activations