INDEX

Explanations

phrases or questions where the response is "Yes."

oai_token-act-pair · gpt-3.5-turbo

affirmative responses or confirmations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 externalToEVAOnly

-0.79

rosse

-0.74

RAW

-0.73

bage

-0.71

versions

-0.70

actionDate

-0.68

 ILCS

-0.68

ojure

-0.67

-0.66

tyard

-0.66

POSITIVE LOGITS

terday

1.23

yes

0.96

Yes

0.91

sir

0.86

YES

0.81

UV

0.74

umph

0.73

YES

0.71

yes

0.71

yne

0.69

Activations Density 0.014%

phrases or questions where the response is "Yes."

affirmative responses or confirmations in the text

No Comments

No Known Activations