INDEX

Explanations

terms related to conflicts, crime, and shady dealings

oai_token-act-pair · gpt-3.5-turbo

terms related to crime and violence

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

iquette

-0.60

lished

-0.59

cyclopedia

-0.55

÷

-0.52

 doesnt

-0.52

wikipedia

-0.52

ategory

-0.52

Ĕ

-0.52

ngth

-0.52

Ď

-0.52

POSITIVE LOGITS

 respectively

0.74

.''.

0.68

)—

0.63

.'"

0.62

).[

0.60

 charism

0.59

.ãĢį

0.57

.).

0.56

"—

0.55

.''

0.54

Activations Density 1.396%

terms related to conflicts, crime, and shady dealings

terms related to crime and violence

No Comments

No Known Activations