INDEX

Explanations

mentions of the word "Dorito" in various contexts

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Dor."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

anwhile

-0.99

WAYS

-0.76

unct

-0.69

 Terrorism

-0.68

 VIDE

-0.65

xual

-0.65

)=(

-0.64

eers

-0.64

ulative

-0.63

pmwiki

-0.63

POSITIVE LOGITS

ÃŃa

0.98

ado

0.97

je

0.93

cas

0.93

oshenko

0.90

chester

0.87

acies

0.87

rance

0.86

iane

0.86

iac

0.83

Activations Density 0.008%

mentions of the word "Dorito" in various contexts

mentions of the name "Dor."

No Comments

No Known Activations