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

angle

-0.84

achu

-0.81

perm

-0.78

ala

-0.76

abs

-0.76

ubes

-0.75

robe

-0.74

editor

-0.74

ranged

-0.73

agonist

-0.72

POSITIVE LOGITS

ufact

0.93

 msec

0.85

 Gard

0.79

ħĭ

0.73

Ago

0.72

ĪĴ

0.71

CVE

0.66

 Lans

0.66

DDR

0.66

 Lawn

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.