INDEX

Explanations

phrases indicating contrast or disagreement

oai_token-act-pair · gpt-3.5-turbo

signals or markers indicating the beginning or end of a text segment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ä»£

-0.72

pecially

-0.69

Unit

-0.60

senal

-0.58

ãĤ©

-0.58

renheit

-0.56

omever

-0.55

è¦ļéĨĴ

-0.55

ular

-0.55

However

-0.55

POSITIVE LOGITS

 nonetheless

1.12

 nevertheless

0.90

etheless

0.80

 still

0.64

 scept

0.64

 anyway

0.64

 beware

0.64

 undeniable

0.62

 doubts

0.62

 caveats

0.60

Activations Density 0.644%

phrases indicating contrast or disagreement

signals or markers indicating the beginning or end of a text segment

No Comments

No Known Activations