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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

creen

-0.70

 Camera

-0.70

aturdays

-0.67

pload

-0.65

 Remix

-0.63

iden

-0.63

emark

-0.63

aby

-0.62

 VIDEOS

-0.62

imir

-0.62

POSITIVE LOGITS

 Okin

0.78

 inflamm

0.71

grass

0.70

 Ferr

0.66

PLA

0.65

 nerve

0.65

 Cambod

0.65

 Southeast

0.64

 Armen

0.63

aneous

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.