INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enburg

-0.71

 Sakuya

-0.71

bryce

-0.70

 Mechdragon

-0.69

ĸļ

-0.68

iri

-0.64

uga

-0.63

 sshd

-0.62

la

-0.62

eff

-0.62

POSITIVE LOGITS

Percent

0.73

atform

0.70

endish

0.70

iliate

0.68

 Proceed

0.63

KN

0.62

ends

0.61

 BELOW

0.60

ilion

0.60

cats

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.