INDEX

Explanations

adjectives describing the seriousness or significance of a situation

oai_token-act-pair · gpt-3.5-turbo

references to reality and truthfulness

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

cius

-0.86

 Beware

-0.84

anwhile

-0.83

 beware

-0.82

clair

-0.79

ometimes

-0.76

alian

-0.75

terson

-0.73

gypt

-0.73

iosis

-0.72

POSITIVE LOGITS

 whatsoever

1.27

 substantive

0.92

nor

0.91

 indication

0.89

 reperc

0.86

 motive

0.83

 reason

0.78

 numerical

0.78

 explanation

0.78

 affiliation

0.77

Activations Density 0.137%

adjectives describing the seriousness or significance of a situation

references to reality and truthfulness

No Comments

No Known Activations