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

vernment

-0.76

indal

-0.67

ugh

-0.66

uchi

-0.62

xual

-0.61

 heal

-0.60

utterstock

-0.59

azel

-0.58

scar

-0.58

 admire

-0.57

POSITIVE LOGITS

apo

0.73

İĭ

0.70

0.67

nikov

0.62

 warr

0.61

urtles

0.60

Lago

0.60

blance

0.60

MU

0.58

Road

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.