INDEX

Explanations

references to software libraries and programming frameworks

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

software entities and proper nouns

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

IntoConstraints

-0.70

CloseOperation

-0.56

 endregion

-0.52

 Walkover

-0.49

featureID

-0.49

ByVersion

-0.48

 Winaray

-0.46

rlpool

-0.46

orghini

-0.46

RegressionTest

-0.46

POSITIVE LOGITS

GNUC

0.78

Brains

0.68

 ModelExpression

0.68

brains

0.60

XmlEnum

0.54

BeginContext

0.51

findpost

0.51

الحياه

0.50

 springfox

0.50

warded

0.50

Activations Density 0.008%

references to software libraries and programming frameworks

software entities and proper nouns

No Comments

No Known Activations