INDEX

Explanations

references to specific measurements or incremental steps in processes

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

every unit of time or measure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 shallo

-0.46

 tipped

-0.42

 apreciar

-0.42

 navigateur

-0.42

 vice

-0.42

providedIn

-0.41

 ligiloj

-0.41

ไม้

-0.41

 promissory

-0.41

 mały

-0.41

POSITIVE LOGITS

RTEX

0.49

Portail

0.46

InputBorder

0.46

 Савезне

0.46

DotNetBar

0.45

 EVERYTHING

0.43

 dAtA

0.43

every

0.43

tissimi

0.43

 every

0.42

Activations Density 0.013%

references to specific measurements or incremental steps in processes

every unit of time or measure

No Comments

No Known Activations