INDEX

Explanations

actions related to driving or traveling by car

oai_token-act-pair · gpt-3.5-turbo

actions related to driving

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Flavoring

-0.75

 Seym

-0.71

Lum

-0.68

roma

-0.65

Ranked

-0.61

enei

-0.60

 lett

-0.59

Published

-0.59

ANN

-0.58

 acknowled

-0.57

POSITIVE LOGITS

wheel

1.03

 away

0.96

bike

0.89

train

0.87

driving

0.87

whe

0.83

 motorcycles

0.81

 driving

0.80

BMW

0.78

 toward

0.77

Activations Density 0.050%

actions related to driving or traveling by car

actions related to driving

No Comments

No Known Activations