INDEX

Explanations

expressions of opinions or beliefs

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ãĤ´ãĥ³

-0.78

Scroll

-0.67

bart

-0.66

 extraord

-0.65

AMY

-0.65

tl

-0.65

cffffcc

-0.64

ãĤ¶

-0.63

patch

-0.63

alsa

-0.62

POSITIVE LOGITS

 respondents

0.91

 unfavorable

0.86

 either

0.82

 they

0.81

 majorities

0.76

 owning

0.74

 lifetime

0.74

 negatively

0.73

 favorably

0.73

 themselves

0.72

Activations Density 0.094%

expressions of opinions or beliefs

No Comments

No Known Activations