INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Advantage

-0.71

 beware

-0.70

Unknown

-0.68

kees

-0.65

vant

-0.65

 Errors

-0.64

 Credits

-0.61

Downloadha

-0.59

#$#$

-0.59

 claims

-0.57

POSITIVE LOGITS

ahime

0.73

iso

0.69

atform

0.66

zilla

0.65

ension

0.65

bringer

0.63

Winged

0.61

uppet

0.61

amin

0.61

rawdownloadcloneembedreportprint

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.