INDEX

Explanations

references to authority figures or sources of authority

oai_token-act-pair · gpt-3.5-turbo

references to authority figures or concepts of authority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Lens

-0.80

 Shal

-0.73

 Lovely

-0.73

 Taste

-0.72

lla

-0.70

itches

-0.69

eful

-0.68

 Cure

-0.65

 Leica

-0.64

nder

-0.64

POSITIVE LOGITS

 authority

1.11

Reviewer

0.98

 delegated

0.95

 vested

0.93

 confir

0.90

 figures

0.88

 conferred

0.87

 estab

0.86

 restraints

0.80

 nomine

0.80

Activations Density 0.017%

references to authority figures or sources of authority

references to authority figures or concepts of authority

No Comments

No Known Activations