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

ngth

-0.80

 Meta

-0.65

MK

-0.64

Artist

-0.62

geist

-0.62

 Moment

-0.61

 FANT

-0.61

 McKenna

-0.61

 FANTASY

-0.61

wl

-0.61

POSITIVE LOGITS

antha

0.87

 crocod

0.83

earances

0.82

usa

0.73

ĳå£«

0.69

atial

0.68

odan

0.68

cair

0.68

yip

0.68

cot

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.