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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

culosis

-0.73

phans

-0.71

Mub

-0.69

reatment

-0.69

 deployments

-0.68

furt

-0.66

 EntityItem

-0.66

wana

-0.65

 GROUP

-0.65

anamo

-0.64

POSITIVE LOGITS

 irrad

0.69

 chrom

0.65

cale

0.63

surface

0.63

fal

0.63

 mate

0.62

ima

0.61

rub

0.61

enza

0.60

vim

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.