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

port

-0.85

iop

-0.74

reply

-0.72

par

-0.71

ippi

-0.69

wx

-0.68

Returns

-0.64

iana

-0.63

photo

-0.63

 Romeo

-0.63

POSITIVE LOGITS

 Marketable

0.78

antha

0.66

 Credits

0.65

 destro

0.64

 Mandal

0.62

©¶æ

0.62

rification

0.62

 VIDE

0.61

¶æ

0.61

 GOODMAN

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.