INDEX

Explanations

speech or dialogue attribution phrases

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

past tense speaker attribution

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

DockStyle

-0.68

webElementXpaths

-0.61

KURZBESCHREIBUNG

-0.59

 للاسماء

-0.58

RegressionTest

-0.56

RegistryLite

-0.54

IsMutable

-0.54

 OMITBAD

-0.54

 ModelExpression

-0.54

parsedMessage

-0.54

POSITIVE LOGITS

glLoadIdentity

0.41

宙

0.41

uland

0.41

 الاطلاع

0.40

mudi

0.39

ptos

0.38

ult

0.38

 otomatig

0.37

portun

0.37

 Musk

0.37

Activations Density 0.021%

speech or dialogue attribution phrases

past tense speaker attribution

No Comments

No Known Activations