INDEX

Explanations

specific mentions of car makes and models

oai_token-act-pair · gpt-3.5-turbo

specific car makes and models mentioned in relation to accidents or incidents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

meric

-0.83

liest

-0.81

ulkan

-0.77

 Sabb

-0.76

 Flavoring

-0.69

astical

-0.66

 portals

-0.66

 Hallow

-0.65

requ

-0.65

ologically

-0.64

POSITIVE LOGITS

 convertible

1.09

 chassis

1.06

 dealership

0.98

 equipped

0.88

 sedan

0.86

 parked

0.85

 fitted

0.80

 buggy

0.79

SUV

0.79

 laptop

0.77

Activations Density 0.279%

specific mentions of car makes and models

specific car makes and models mentioned in relation to accidents or incidents

No Comments

No Known Activations