INDEX

Explanations

prepositions indicating direction

oai_token-act-pair · gpt-3.5-turbo

conjunctions and phrases indicating relationships

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

 Panda

-0.78

 Democr

-0.76

 Pony

-0.75

 Clever

-0.72

 Welch

-0.69

 Freak

-0.69

 Fine

-0.68

Yao

-0.67

 Examiner

-0.65

FAT

-0.65

POSITIVE LOGITS

rogens

1.04

rogen

1.04

0.89

Against

0.81

 Against

0.75

against

0.73

through

0.73

\<

0.71

excluding

0.71

near

0.71

Activations Density 0.073%

prepositions indicating direction

conjunctions and phrases indicating relationships

No Comments

No Known Activations