INDEX

Explanations

occurrences of the letter 'm' in various contexts

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

Objective-C .m files

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

 GoogleFonts

-0.56

 greateſt

-0.50

fromnode

-0.47

 vectorielles

-0.47

errHandler

-0.46

adpleegd

-0.46

XmlEnum

-0.43

 estekak

-0.42

 prêts

-0.42

 ſta

-0.42

POSITIVE LOGITS

0.89

nonatomic

0.64

 nonatomic

0.62

0.57

jure

0.53

 AssemblyTitle

0.50

BASEPATH

0.49

 NgModule

0.48



0.48

hpp

0.46

Activations Density 0.010%

occurrences of the letter 'm' in various contexts

Objective-C .m files

No Comments

No Known Activations