INDEX

Explanations

words related to preferences or things that are liked or favored

oai_token-act-pair · gpt-3.5-turbo

words that indicate popularity or preference

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ural

-0.85

inas

-0.78

ijk

-0.77

ufact

-0.76

TPPStreamerBot

-0.76

amping

-0.73

arty

-0.72

heed

-0.72

abad

-0.69

acial

-0.68

POSITIVE LOGITS

 favorites

0.94

 favorite

0.91

Favorite

0.84

 haunt

0.81

 Favor

0.81

 Favorite

0.79

é¾įå

0.77

 favourites

0.77

é¾įå¥ĳå£«

0.76

è¦

0.74

Activations Density 0.013%

words related to preferences or things that are liked or favored

words that indicate popularity or preference

No Comments

No Known Activations