INDEX

Explanations

numerical values and their associated formatting specifications

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

ISO-8859-1 charset

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

 transfieras

-0.57

AutoField

-0.55

Diwedd

-0.54

findpost

-0.54

messageInfo

-0.52

Batis

-0.50

.*")]

-0.50

mergeFrom

-0.49

setupUi

-0.49

keyColumn

-0.49

POSITIVE LOGITS

lusconi

0.76

frost

0.70

adaptiveStyles

0.60

 Maradona

0.55

isNameExpr

0.54

noscript

0.53

 frost

0.53

fjspx

0.52

 uLocal

0.50

 كورة

0.49

Activations Density 0.003%

numerical values and their associated formatting specifications

ISO-8859-1 charset

No Comments

No Known Activations