INDEX

Explanations

numbers and technical terms

oai_token-act-pair · gpt-3.5-turbo

references to numeric data and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

esides

-0.60

,)

-0.57

-0.56

 resil

-0.53

),"

-0.52

.),

-0.50

="/

-0.50

"),

-0.50

.}

-0.49

portation

-0.48

POSITIVE LOGITS

1.92

(?,

1.54

(.

1.49

([

1.49

(-

1.47

(_

1.46

(!

1.45

(/

1.44

('

1.42

((

1.40

Activations Density 0.315%

numbers and technical terms

references to numeric data and measurements

No Comments

No Known Activations