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

cknowled

-0.73

 GOODMAN

-0.71

beh

-0.66

 crane

-0.65

 demonstr

-0.64

inness

-0.63

 Cage

-0.63

ricks

-0.62

 clauses

-0.62

WTO

-0.62

POSITIVE LOGITS

ieri

0.80

 Gutenberg

0.74

itably

0.69

nesia

0.68

 Kraken

0.66

 Whitman

0.66

sburg

0.65

 thous

0.65

 Fortune

0.64

elia

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.