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

dq

-0.72

issue

-0.70

é»Ĵ

-0.68

thora

-0.64

JD

-0.63

issues

-0.63

cha

-0.63

 pest

-0.63

 Celt

-0.62

RPG

-0.62

POSITIVE LOGITS

waukee

0.71

 Ending

0.71

atorium

0.66

ennial

0.64

achusetts

0.64

ulic

0.64

rious

0.63

river

0.62

 Mile

0.62

 Thro

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.