INDEX

Explanations

phrases indicating the speaker is offering a statement or opinion

oai_token-act-pair · gpt-3.5-turbo

expressions indicating agreement or support

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

 metic

-0.70

 clipping

-0.70

 clones

-0.69

 pigeon

-0.68

 chained

-0.67

 flowering

-0.66

 adolesc

-0.66

 reflex

-0.66

 cloning

-0.66

 welf

-0.64

POSITIVE LOGITS

ï¸ı

1.06

ternity

0.92

uthor

0.88

×Ķ

0.84

ortunate

0.84

audi

0.83

âĶĢâĶĢ

0.82

ever

0.81

\-

0.81

there

0.80

Activations Density 0.142%

phrases indicating the speaker is offering a statement or opinion

expressions indicating agreement or support

No Comments

No Known Activations