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

glass

-0.92

EStreamFrame

-0.72

gat

-0.72

 Gleaming

-0.69

Haunted

-0.67

Prop

-0.64

watching

-0.64

lifting

-0.63

 Thoughts

-0.62

 Lyme

-0.62

POSITIVE LOGITS

guyen

0.71

annel

0.71

heit

0.64

bourg

0.62

 differentiation

0.62

 exception

0.60

yz

0.59

ayette

0.59

 unanim

0.59

ufact

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.