INDEX

Explanations

terms related to offensive language or content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

SIGINT

-0.53

 Schar

-0.44

 center

-0.43

 magazine

-0.42

 controlled

-0.42

MediaType

-0.41

 Controlled

-0.41

 Koch

-0.41

 Group

-0.41

 Center

-0.41

POSITIVE LOGITS

:✨

1.05

DockStyle

0.70

AsUp

0.66

UnknownFieldSet

0.66

Jeografia

0.65

 للاسماء

0.65

 näytte

0.60

SharedCtor

0.60

帖最后由

0.60

offensive

0.58

Activations Density 0.322%

terms related to offensive language or content

No Comments

No Known Activations