INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

estern

-0.89

Lear

-0.69

inders

-0.68

 Craw

-0.65

aughs

-0.65

ikuman

-0.63

INA

-0.62

INTON

-0.62

Master

-0.61

elin

-0.61

POSITIVE LOGITS

icago

0.78

cially

0.70

grass

0.70

 occupations

0.69

 ornament

0.64

 praises

0.63

 agitation

0.62

aurus

0.62

 busiest

0.61

sonian

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.