INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

gran

-0.85

gage

-0.83

ersive

-0.82

regor

-0.80

gas

-0.79

nesia

-0.78

urgy

-0.74

ampunk

-0.73

nesota

-0.73

anchester

-0.71

POSITIVE LOGITS

 concess

0.73

CTV

0.66

pload

0.66

 Cortana

0.65

 Rahman

0.64

 incent

0.63

 Shaw

0.63

Kor

0.62

 Verse

0.62

 viewed

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.