INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

istries

-0.73

rums

-0.70

erness

-0.69

aii

-0.68

enegger

-0.67

lain

-0.65

idays

-0.63

 atheist

-0.63

 Athe

-0.63

athe

-0.62

POSITIVE LOGITS

othal

0.69

uci

0.67

ãĤ®

0.66

ocation

0.64

MU

0.62

PU

0.61

uner

0.61

vic

0.59

unicip

0.59

 Municipal

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.