INDEX

Explanations

announcements or statements of action being taken by organizations or entities

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

 Explan

-0.81

Appearance

-0.72

 inexper

-0.72

 assurances

-0.68

 perception

-0.65

gettable

-0.64

 contrasted

-0.64

answered

-0.64

ortun

-0.63

 understandable

-0.63

POSITIVE LOGITS

©¶æ

0.82

 quitting

0.78

 suspending

0.78

 officially

0.76

 discontin

0.75

 partnered

0.74

 laun

0.73

 postp

0.72

 quit

0.72

clusively

0.71

Activations Density 0.243%

announcements or statements of action being taken by organizations or entities

No Comments

No Known Activations