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

éĩ

-0.74

Ö¼

-0.71

hub

-0.66

 lunar

-0.65

 subst

-0.65

ãĥ¼ãĥĨãĤ£

-0.63

 indo

-0.63

 Atmosp

-0.63

 moon

-0.62

 Lund

-0.62

POSITIVE LOGITS

+(

0.76

haps

0.75

stories

0.72

rison

0.72

aughs

0.70

obbies

0.69

agher

0.69

retty

0.69

riots

0.68

TRUMP

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.