INDEX

Explanations

statistics related to likelihood or probability

oai_token-act-pair · gpt-3.5-turbo

phrases indicating statistical likelihood or probabilities associated with various groups or conditions

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

IFrame

Link

Negative Logits

zeb

-0.94

uart

-0.76

inelli

-0.76

wagen

-0.75

andan

-0.74

kind

-0.72

dust

-0.72

ornia

-0.71

ylan

-0.71

sterdam

-0.71

POSITIVE LOGITS

Øª

0.79

 than

0.74

 divorce

0.72

 likely

0.71

 prey

0.69

âĢł

0.68

 incarcer

0.67

 infer

0.66

 prone

0.65

 respondents

0.65

Activations Density 0.030%

statistics related to likelihood or probability

phrases indicating statistical likelihood or probabilities associated with various groups or conditions

No Known Activations