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

gow

-0.73

icate

-0.66

Pru

-0.63

galitarian

-0.62

ature

-0.62

hyde

-0.62

ivo

-0.61

 Staples

-0.61

OUT

-0.61

igel

-0.60

POSITIVE LOGITS

paio

0.75

unta

0.68

 surv

0.63

urance

0.62

neg

0.61

 exercised

0.60

 civilian

0.60

ynes

0.60

reditary

0.59

romy

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.