INDEX

Explanations

terminologies related to classification and naming conventions

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

definition and usage of terms

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

 priming

-0.43

 Celestial

-0.42

MemberId

-0.42

 CIVIL

-0.41

 Civil

-0.41

 Merid

-0.41

 Schell

-0.41

 Municipal

-0.40

 sanctuary

-0.40

 Schar

-0.40

POSITIVE LOGITS

WebElementEntity

0.57

MigrationBuilder

0.56

MLLoader

0.52

 suele

0.49

 saites

0.48

verwijspagina

0.48

 resourceCulture

0.48

 ujednoznacz

0.48

 często

0.48

enumi

0.48

Activations Density 0.039%

terminologies related to classification and naming conventions

definition and usage of terms

No Comments

No Known Activations