INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

blind

-0.76

 scrimmage

-0.62

hov

-0.59

etc

-0.59

 Pigs

-0.59

market

-0.59

 market

-0.58

Hod

-0.58

avez

-0.58

 chains

-0.58

POSITIVE LOGITS

 reassuring

0.74

hiba

0.74

ilus

0.73

adata

0.68

ector

0.67

lus

0.66

sylv

0.66

 millenn

0.66

paio

0.64

 pregn

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.