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

 Dickinson

-0.67

 Hobby

-0.67

 Goodwin

-0.64

Īè

-0.63

 Scotia

-0.63

 Garland

-0.61

ESCO

-0.59

hart

-0.59

 mortality

-0.59

 Netflix

-0.58

POSITIVE LOGITS

ioch

0.92

ctr

0.78

ãĥĺãĥ©

0.74

ustomed

0.74

claimer

0.72

terior

0.71

cture

0.70

 sensed

0.69

ettings

0.69

inia

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.