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

 Carbuncle

-0.89

thood

-0.82

estyles

-0.81

å£«

-0.80

 Moines

-0.80

ghai

-0.78

zona

-0.78

BILITIES

-0.76

etics

-0.76

gio

-0.75

POSITIVE LOGITS

bip

0.75

 arsen

0.70

 offending

0.70

 mand

0.68

 claimant

0.67

 demanding

0.67

 deleg

0.66

 unmarked

0.66

 concession

0.65

 blocking

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.