INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 commod

-0.69

cra

-0.67

 shut

-0.64

 Mush

-0.64

inj

-0.64

 Filip

-0.63

 unlaw

-0.62

 entrepreneurs

-0.60

 scapego

-0.60

 partnerships

-0.60

POSITIVE LOGITS

lance

0.83

rica

0.80

vant

0.78

mental

0.78

ournal

0.77

dn

0.76

URA

0.76

lass

0.74

rets

0.74

UCT

0.74

Activations Density 0.000%

No Known Activations

This feature has no known activations.