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

rage

-0.70

growth

-0.67

vale

-0.65

 delaying

-0.64

 Anger

-0.64

isSpecialOrderable

-0.64

zag

-0.63

gyn

-0.63

cery

-0.61

puff

-0.61

POSITIVE LOGITS

Reviewer

0.67

 axes

0.65

 fronts

0.64

nants

0.63

uggle

0.62

ocene

0.62

aut

0.62

 Planetary

0.61

sonian

0.60

onnaissance

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.