INDEX

Explanations

references to live events and announcements related to fighting

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

fighting events and wrestling

np_acts-logits-general · gemini-2.0-flash

fight results and wrestling

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

ftagPool

-0.59

oa̍t

-0.58

>{@

-0.55

 AssemblyProduct

-0.52

UIControlState

-0.51

richTextPanel

-0.51

 nominating

-0.50

ensement

-0.50

principalColumn

-0.48

 Jinping

-0.47

POSITIVE LOGITS

 ring

0.83

 rings

0.72

 Ring

0.69

 promotion

0.68

Ring

0.66

 wrestling

0.59

 Rings

0.59

 Smack

0.59

rings

0.59

Rings

0.58

Activations Density 0.127%

references to live events and announcements related to fighting

fighting events and wrestling

fight results and wrestling

No Comments

No Known Activations