INDEX

Explanations

terms related to investigation and analysis within a research context

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

verbs ending in ize

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 nenhuma

-0.36

 Fores

-0.35

 nenhum

-0.35

ApiModelProperty

-0.34

Życiorys

-0.34

ม่

-0.34

 OnInit

-0.33

 plátano

-0.33

 Waterfront

-0.33

 vieille

-0.33

POSITIVE LOGITS

AndEndTag

0.70

fjspx

0.52

HandlerContext

0.49

 JpaRepository

0.48

 nakalista

0.48

basicConfig

0.48

queryInterface

0.47

+#+#

0.47

/**

0.47

tomans

0.45

Activations Density 0.047%

terms related to investigation and analysis within a research context

verbs ending in ize

No Comments

No Known Activations