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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Cure

-0.75

Reply

-0.74

DOS

-0.73

tox

-0.66

 Controls

-0.65

 crawl

-0.64

controlled

-0.62

ternity

-0.62

Rogue

-0.61

Imp

-0.61

POSITIVE LOGITS

assic

0.71

illet

0.68

ideon

0.66

cyl

0.66

 Earl

0.65

kj

0.64

 Sabha

0.62

idon

0.62

ricanes

0.61

 Nickel

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.