INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Filename

-0.74

azaki

-0.65

brate

-0.62

bal

-0.61

rational

-0.61

ply

-0.60

consumer

-0.60

iod

-0.59

stic

-0.59

Î²

-0.58

POSITIVE LOGITS

 Seym

0.79

Ü

0.74

 shootout

0.73

eny

0.72

dies

0.67

merce

0.67

venge

0.66

 seiz

0.66

wic

0.66

 gentlemen

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.