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

ellar

-0.87

 unseen

-0.68

»Ĵ

-0.66

 eleph

-0.64

perse

-0.64

 Hilbert

-0.61

Reviewer

-0.61

encia

-0.60

 Likely

-0.58

cipline

-0.58

POSITIVE LOGITS

ocity

0.76

oco

0.73

ast

0.70

itude

0.68

equ

0.67

berman

0.66

asted

0.65

asting

0.65

isine

0.64

BAT

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.