INDEX

Explanations

statistical likelihoods or probabilities related to various characteristics or behaviors

oai_token-act-pair · gpt-3.5-turbo

phrases that express statistical likelihood or probability related to various groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

zeb

-0.97

andan

-0.76

ylan

-0.76

loo

-0.72

dust

-0.72

inelli

-0.68

athom

-0.68

inosaur

-0.67

gem

-0.67

ream

-0.67

POSITIVE LOGITS

 likely

0.75

 than

0.74

âĢł

0.72

 prone

0.72

Øª

0.69

 encountering

0.69

 respondents

0.68

 prey

0.68

 infer

0.67

 underest

0.65

Activations Density 0.036%

statistical likelihoods or probabilities related to various characteristics or behaviors

phrases that express statistical likelihood or probability related to various groups

No Comments

No Known Activations