INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

warts

-0.67

 glaring

-0.65

ebted

-0.65

aez

-0.64

uin

-0.62

odon

-0.62

dc

-0.62

owan

-0.61

 sheer

-0.61

Ga

-0.61

POSITIVE LOGITS

Cho

0.74

 Discrimination

0.71

Component

0.71

 Puzzles

0.71

 Cyprus

0.70

Dep

0.69

 Malaysia

0.69

»

0.69

Kids

0.69

 Rohing

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.