INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

EXT

-0.72

ieth

-0.68

emort

-0.66

uku

-0.64

inational

-0.63

ahn

-0.62

 Radio

-0.62

autions

-0.61

 communications

-0.61

ym

-0.60

POSITIVE LOGITS

¥µ

0.85

Ĥª

0.83

zek

0.78

 rake

0.66

vasive

0.64

rants

0.61

urat

0.61

regon

0.60

skirts

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.