INDEX

Explanations

phrases indicating agreement or disagreement with a statement

oai_token-act-pair · gpt-3.5-turbo

assertions of correctness or authority in opinions and decisions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 resil

-0.72

 cumbers

-0.69

 vying

-0.69

 overseen

-0.67

gall

-0.66

staking

-0.65

ipal

-0.64

 intric

-0.64

 embroiled

-0.63

 scrim

-0.63

POSITIVE LOGITS

 Wrong

0.74

ovi

0.67

 Lange

0.65

 Citation

0.65

 Â¶

0.65

âĵĺ

0.63

 Luxem

0.63

ABE

0.62

{\

0.61

 Newport

0.61

Activations Density 0.208%

phrases indicating agreement or disagreement with a statement

assertions of correctness or authority in opinions and decisions

No Comments

No Known Activations