INDEX

Explanations

adjectives indicating judgment or evaluation

oai_token-act-pair · gpt-3.5-turbo

phrases or expressions indicating absence, negation, or futility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ahime

-0.84

[|

-0.73

majority

-0.61

lance

-0.60

 sometime

-0.58

gart

-0.58

ghan

-0.57

asus

-0.57

olds

-0.57

AX

-0.56

POSITIVE LOGITS

except

1.03

 whatsoever

1.01

 except

0.98

 resembling

0.83

 besides

0.76

nor

0.73

imilar

0.72

Except

0.71

ificant

0.70

ensical

0.69

Activations Density 0.172%

adjectives indicating judgment or evaluation

phrases or expressions indicating absence, negation, or futility

No Comments

No Known Activations