INDEX

Explanations

references to financial market terms and negotiations

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

Tokens after the max activating token are unusual words

np_acts-logits-general · gemini-2.0-flash

poker terminology

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

ValueStyle

-0.65

出版年

-0.58

PerformLayout

-0.54

 getSystem

-0.54

Życiorys

-0.52

 ricette

-0.51

 муніципалі

-0.51

 urbanas

-0.50

 sanitarias

-0.50

 sanitaires

-0.50

POSITIVE LOGITS

 tournament

0.73

OGND

0.72

 Poker

0.71

 poker

0.70

MTT

0.68

 heads

0.67

PLO

0.66

 betweenstory

0.65

 rebu

0.65

 bracelet

0.63

Activations Density 0.056%

references to financial market terms and negotiations

Tokens after the max activating token are unusual words

poker terminology

No Comments

No Known Activations