INDEX

Explanations

phrases where a quoted statement is mentioned

oai_token-act-pair · gpt-3.5-turbo

quotation marks and brackets indicating speech or citation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Woody

-0.70

Lin

-0.69

Beg

-0.64

 Tart

-0.62

 pitch

-0.62

Man

-0.62

 stiff

-0.62

 minor

-0.61

 Victory

-0.61

 Columbus

-0.59

POSITIVE LOGITS

without

1.63

because

1.54

against

1.53

with

1.48

during

1.45

within

1.44

into

1.43

whose

1.40

until

1.38

before

1.38

Activations Density 0.226%

phrases where a quoted statement is mentioned

quotation marks and brackets indicating speech or citation

No Comments

No Known Activations