INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 sacrific

-0.84

utical

-0.79

ĳå£«

-0.72

arin

-0.69

aq

-0.68

wered

-0.66

]+

-0.65

cies

-0.65

hiba

-0.65

 Lovecraft

-0.65

POSITIVE LOGITS

scribe

0.75

Sync

0.72

Shift

0.67

gradient

0.66

Press

0.63

 distraction

0.63

Enlarge

0.63

tons

0.63

Screen

0.63

Screenshot

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.