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

izen

-0.82

inal

-0.79

iance

-0.73

onia

-0.72

mand

-0.71

ibe

-0.69

illian

-0.69

YR

-0.69

inals

-0.68

ellig

-0.68

POSITIVE LOGITS

awa

0.94

 hawk

0.80

âĸ¬

0.73

 thous

0.73

jet

0.65

ãĥīãĥ©ãĤ´ãĥ³

0.64

 enthusi

0.64

 referen

0.64

 hither

0.64

EVA

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.