INDEX

Explanations

specific nouns and terms related to authority, classification, and structure in language or programming contexts

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

A, A, A

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

 propOrder

-0.65

tagHelperRunner

-0.59

windowFixed

-0.56

 незавершена

-0.54

 resourceCulture

-0.51

⟬

-0.51

 Scopus

-0.50

RequestMapping

-0.50

quo

-0.49

verifyException

-0.49

POSITIVE LOGITS

 jongen

0.46

 telefónica

0.43

 dragón

0.42

 hoogte

0.42

 desmotivaciones

0.41

 cantora

0.40

 colgante

0.40

 mandatario

0.40

avond

0.39

 refirió

0.38

Activations Density 0.049%

specific nouns and terms related to authority, classification, and structure in language or programming contexts

A, A, A

No Comments

No Known Activations