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

arters

-0.77

utenant

-0.76

ews

-0.75

alion

-0.74

è£ħ

-0.73

shirts

-0.70

OTO

-0.70

ART

-0.70

 achievable

-0.68

rolet

-0.68

POSITIVE LOGITS

cial

0.75

adjusted

0.69

temp

0.68

)</

0.68

cing

0.64

ã

0.63

trial

0.62

gy

0.61

 Loving

0.61

secret

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.