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

cial

-0.77

ische

-0.75

 divest

-0.66

Sham

-0.63

 Schwar

-0.63

 extracting

-0.62

 cant

-0.62

 derivative

-0.62

 rethink

-0.60

uer

-0.60

POSITIVE LOGITS

£ı

0.77

Ã£

0.75

uphem

0.69

IRO

0.63

bh

0.62

 Ichigo

0.61

anas

0.61

 Codec

0.60

vironments

0.59

 Ying

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.