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

"-

-0.76

uv

-0.72

Drag

-0.71

hooting

-0.70

MAG

-0.69

Vari

-0.67

"_

-0.65

Org

-0.65

pmwiki

-0.65

POSITIVE LOGITS

ħĭ

0.67

zee

0.66

 goodbye

0.64

ukemia

0.64

 classmate

0.63

lete

0.63

 clashed

0.60

zees

0.59

esta

0.59

cedented

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.