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

-0.84

hov

-0.75

otin

-0.66

vet

-0.64

erent

-0.64

PsyNetMessage

-0.64

Vir

-0.64

uv

-0.63

 Lithuan

-0.62

 elev

-0.61

POSITIVE LOGITS

sonian

0.70

paio

0.66

 busted

0.65

fo

0.64

ayne

0.63

ondo

0.62

 statewide

0.60

akespeare

0.59

psons

0.59

iste

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.