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

affle

-0.70

ptive

-0.67

ence

-0.65

ouse

-0.63

oped

-0.63

ioned

-0.62

*/(

-0.62

Word

-0.61

Fay

-0.59

Ô

-0.59

POSITIVE LOGITS

avery

0.76

avers

0.73

 Territories

0.66

bill

0.64

 Weaver

0.64

crew

0.63

STEM

0.62

eks

0.61

 underest

0.59

bos

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.