INDEX

Explanations

references to mountain-related terms

oai_token-act-pair · gpt-3.5-turbo

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

uel

-0.83

encia

-0.79

 Machina

-0.78

lest

-0.76

BACK

-0.75

orate

-0.73

ually

-0.72

tle

-0.71

tions

-0.70

uality

-0.70

POSITIVE LOGITS

 biking

1.14

 footh

0.97

 laure

0.96

 climbers

0.91

 ridge

0.89

lake

0.81

 climbing

0.80

 lions

0.79

 bike

0.78

 Bike

0.77

Activations Density 0.051%

references to mountain-related terms

No Comments

No Known Activations