INDEX

Explanations

mentions of steering-related terms

oai_token-act-pair · gpt-3.5-turbo

references to steering mechanisms or related terms in automotive contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ropolitan

-0.80

ISC

-0.70

ABE

-0.69

Veter

-0.67

mercial

-0.67

mpeg

-0.66

 Kinnikuman

-0.66

gdala

-0.65

Export

-0.64

 Anthem

-0.63

POSITIVE LOGITS

 steering

1.08

wheel

1.03

 wheel

1.03

anship

0.99

 steer

0.97

 steered

0.90

 levers

0.87

rud

0.87

wagon

0.78

chair

0.78

Activations Density 0.007%

mentions of steering-related terms

references to steering mechanisms or related terms in automotive contexts

No Comments

No Known Activations