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

rouse

-0.63

 favorably

-0.63

 buck

-0.63

 compromises

-0.62

 fibre

-0.62

BC

-0.61

JB

-0.61

 fuelled

-0.61

 IMAGES

-0.60

 Punk

-0.60

POSITIVE LOGITS

İĭ

0.81

ĺħ

0.76

yre

0.75

Ã±

0.75

gor

0.73

ugi

0.71

agna

0.69

©¶æ¥µ

0.69

center

0.68

 plur

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.