INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

aceous

-0.76

umers

-0.75

hyde

-0.72

bern

-0.72

 endings

-0.68

 wastes

-0.68

iotic

-0.67

addons

-0.66

azes

-0.65

iets

-0.65

POSITIVE LOGITS

stood

0.63

Govern

0.62

 applause

0.59

DEP

0.58

 cheers

0.58

uv

0.58

signed

0.58

 Garfield

0.57

laughter

0.56

ceed

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.