INDEX

Explanations

questions or statements containing contractions

oai_token-act-pair · gpt-3.5-turbo

negative contractions expressing doubt or uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

anwhile

-0.75

 rall

-0.72

 Axis

-0.69

 Powered

-0.69

 exha

-0.67

 hemor

-0.66

 newcom

-0.65

 populated

-0.64

 withd

-0.63

 disabled

-0.63

POSITIVE LOGITS

't

1.83

ny

1.08

ÃŃ

1.00

itely

0.97

0.94

ned

0.89

Â´

0.85

ited

0.85

iting

0.84

ad

0.84

Activations Density 0.072%

questions or statements containing contractions

negative contractions expressing doubt or uncertainty

No Comments

No Known Activations