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

abal

-0.75

 degree

-0.67

ayn

-0.66

adm

-0.65

 cardinal

-0.65

ilo

-0.65

liness

-0.64

tained

-0.63

ly

-0.63

ln

-0.62

POSITIVE LOGITS

krit

0.86

 Jackets

0.72

 teasp

0.71

 Investigations

0.67

ãĥķãĤ©

0.64

 Cobra

0.62

Fif

0.61

srf

0.61

 eleph

0.60

{"

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.