INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

idates

-0.80

 chanting

-0.70

Ħ¢

-0.69

zees

-0.66

hovah

-0.64

mins

-0.63

igham

-0.63

zee

-0.62

mia

-0.62

POSITIVE LOGITS

0.75

creen

0.70

 conceal

0.62

ãģķ

0.60

imm

0.60

ãĥ´

0.60

 tile

0.59

trace

0.57

brow

0.57

pread

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.