INDEX

Explanations

phrases indicating past actions or experiences

oai_token-act-pair · gpt-3.5-turbo

phrases indicating strong opposition or conflict

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

rous

-0.62

upper

-0.62

ogical

-0.61

 optic

-0.60

rial

-0.59

LIB

-0.58

 ransom

-0.57

orus

-0.57

 theaters

-0.57

ery

-0.56

POSITIVE LOGITS

ĪĴ

0.91

 lately

0.84

recent

0.82

now

0.78

 hasn

0.71

progress

0.69

alach

0.69

ierrez

0.68

 recently

0.66

ateur

0.66

Activations Density 0.724%

phrases indicating past actions or experiences

phrases indicating strong opposition or conflict

No Comments

No Known Activations