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

SPONSORED

-0.81

pread

-0.66

 sexist

-0.63

 park

-0.62

 perspect

-0.62

 masc

-0.60

 Witt

-0.59

ellar

-0.58

ãĥ¼ãĥ

-0.58

 passers

-0.57

POSITIVE LOGITS

iak

0.80

phabet

0.79

atform

0.76

dayName

0.75

ipher

0.72

inctions

0.72

iates

0.72

weekly

0.72

rius

0.71

oxide

0.71

Activations Density 0.000%

No Known Activations

This feature has no known activations.