INDEX

Explanations

HTML tags and navigation elements in a document

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

html list items

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

Personendaten

-0.69

 uLocal

-0.60

 MainAxisSize

-0.59

WebElementEntity

-0.58

 OMITBAD

-0.54

styleType

-0.53

AsUp

-0.53

KommentareTeilen

-0.53

cellence

-0.52

rinology

-0.51

POSITIVE LOGITS

 psicológica

0.31

fendi

0.31

 femininas

0.30

 Tratado

0.30

 eingeladen

0.29

 undangan

0.29

unnitel

0.29

 ricca

0.29

 demás

0.29

 uživ

0.28

Activations Density 0.010%

HTML tags and navigation elements in a document

html list items

No Comments

No Known Activations