INDEX

Explanations

words related to inappropriate or unacceptable behavior

oai_token-act-pair · gpt-3.5-turbo

instances of the term "uncertain" or its variations in context

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

å§«

-0.92

uyomi

-0.91

 Solitaire

-0.75

=-=-=-=-

-0.74

heid

-0.72

=-=-=-=-=-=-=-=-

-0.71

MENT

-0.71

 fronts

-0.70

Downloadha

-0.70

utenant

-0.69

POSITIVE LOGITS

ursed

0.99

oded

0.91

ount

0.89

redited

0.88

reated

0.87

ooked

0.87

unc

0.81

aleb

0.81

icated

0.81

ashed

0.80

Activations Density 0.004%

words related to inappropriate or unacceptable behavior

instances of the term "uncertain" or its variations in context

No Known Activations