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

IFrame

Link

Negative Logits

heit

-0.78

sonian

-0.75

cale

-0.75

iage

-0.74

 watershed

-0.70

saf

-0.69

rior

-0.69

hari

-0.67

atibility

-0.66

riage

-0.65

POSITIVE LOGITS

ãĤ¤ãĥĪ

0.85

 encour

0.73

Redd

0.72

Discuss

0.70

ãĤ´ãĥ³

0.66

 Notting

0.64

 ingred

0.64

Offic

0.62

ãĥĳ

0.62

 pubs

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.