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

bound

-0.84

borg

-0.81

ZI

-0.78

talking

-0.76

sheets

-0.76

psych

-0.75

yon

-0.74

jug

-0.74

artifacts

-0.73

velt

-0.73

POSITIVE LOGITS

 Ellis

0.79

 Cooke

0.77

 Childhood

0.73

 Â¶

0.69

 Kers

0.68

 Seed

0.67

///

0.66

ab

0.66

Lee

0.66

 Decl

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.