INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

pmwiki

-0.92

atown

-0.79

 Physicians

-0.74

ople

-0.73

DonaldTrump

-0.72

isson

-0.71

cca

-0.67

acs

-0.67

poke

-0.66

eking

-0.64

POSITIVE LOGITS

oun

0.79

ulet

0.78

 Petraeus

0.67

irgin

0.66

=-=-=-=-

0.66

rist

0.65

tyr

0.65

arya

0.64

vp

0.60

:{

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.