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

Ò

-0.79

cham

-0.76

uyomi

-0.75

taboola

-0.71

Ð²

-0.71

CHA

-0.70

SPONSORED

-0.70

Vill

-0.69

 awoken

-0.69

 wondered

-0.69

POSITIVE LOGITS

obby

0.75

ars

0.66

arcity

0.64

 retention

0.63

igraph

0.62

apsed

0.61

renched

0.61

ria

0.60

izza

0.60

iquid

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.