INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ãĤ©

-0.73

ALD

-0.72

FACE

-0.69

atur

-0.69

 Dent

-0.68

BLIC

-0.67

asonic

-0.67

onom

-0.65

vantage

-0.64

olicy

-0.63

POSITIVE LOGITS

 kitten

0.75

é¾įåĸļå£«

0.73

 scraps

0.73

 kittens

0.70

Snow

0.70

INTON

0.67

 keywords

0.65

 shred

0.65

batch

0.63

 sugg

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.