INDEX

Explanations

mentions of documents and details related to investigations or disclosures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Videos

-0.73

 Videos

-0.71

 videos

-0.69

 films

-0.68

 Interviews

-0.65

ArgsConstructor

-0.64

 documentaries

-0.64

 Photographs

-0.64

 movies

-0.64

 Reports

-0.64

POSITIVE LOGITS

 piece

1.25

 article

1.14

 document

1.12

 passage

0.90

 sentence

0.87

 poem

0.83

piece

0.81

 message

0.81

 item

0.80

document

0.77

Activations Density 0.615%

mentions of documents and details related to investigations or disclosures

No Comments

No Known Activations