INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ropy

-0.76

 Colonial

-0.69

 Territories

-0.69

Merit

-0.69

 Liberty

-0.64

 Orbital

-0.63

 Wanted

-0.63

 Offline

-0.63

 Disorders

-0.62

 Held

-0.60

POSITIVE LOGITS

earch

0.72

ĸļ

0.70

ework

0.66

 curtain

0.65

 compliment

0.64

issance

0.64

ãģĨ

0.64

eus

0.63

 Rasm

0.63

\">

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.