INDEX

Explanations

references to motorsports companies

oai_token-act-pair · gpt-3.5-turbo

mentions of automotive companies, specifically related to "Motors."

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

lihood

-0.79

 Kafka

-0.72

 Liang

-0.69

 Bern

-0.69

 Defenders

-0.68

isson

-0.68

ylum

-0.67

 Castro

-0.67

 Cullen

-0.65

LY

-0.64

POSITIVE LOGITS

wagen

0.92

puter

0.92

otive

0.91

cycle

0.87

obiles

0.85

negie

0.85

itialized

0.83

oline

0.80

ports

0.78

ageddon

0.77

Activations Density 0.009%

references to motorsports companies

mentions of automotive companies, specifically related to "Motors."

No Comments

No Known Activations