INDEX

Explanations

phrases related to legal or official statements

oai_token-act-pair · gpt-3.5-turbo

the word "the."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

successfully

-0.89

 cannabin

-0.81

etheless

-0.76

cious

-0.76

enfranch

-0.73

ardless

-0.72

emin

-0.71

apon

-0.70

amphetamine

-0.69

orate

-0.68

POSITIVE LOGITS

 narrator

0.97

said

0.95

 reviewer

0.83

 researcher

0.82

 said

0.81

 seller

0.79

 former

0.78

 unnamed

0.78

 latter

0.74

 interviewer

0.74

Activations Density 0.063%

phrases related to legal or official statements

the word "the."

No Comments

No Known Activations