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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pires

-0.76

Pry

-0.74

 âĨĳ

-0.73

ptin

-0.71

ĸļ

-0.69

Lug

-0.68

ulse

-0.67

ĵĺ

-0.62

 pitted

-0.62

ourced

-0.60

POSITIVE LOGITS

tto

0.71

sonian

0.71

sports

0.68

tesy

0.67

Recomm

0.62

ateg

0.61

TY

0.60

natureconservancy

0.60

coming

0.59

LECT

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.