INDEX

Explanations

terms related to fire extinguishing systems and their features

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

firefighting

np_acts-logits-general · gemini-2.5-flash-lite

mentions of firefighting or extinguishing — references to fires, firefighting personnel, equipment, systems, or actions to put fires out.

oai_token-act-pair · gpt-5-mini Triggered by @vetterc0

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

 AssemblyCompany

-0.62

 GenerationType

-0.62

 NSCoder

-0.61

 nakalista

-0.56

angliski

-0.56

inSlope

-0.56

LEncoder

-0.53

oredCriteria

-0.52

 Administrativna

-0.52

migrationBuilder

-0.52

POSITIVE LOGITS

Extinguishing

0.40

 falla

0.35

po

0.35

 unit

0.34

pel

0.33

UNIT

0.32

 alkyl

0.32

 firefighting

0.32

unit

0.32

 spill

0.31

Activations Density 0.096%

terms related to fire extinguishing systems and their features

firefighting

mentions of firefighting or extinguishing — references to fires, firefighting personnel, equipment, systems, or actions to put fires out.

No Comments

No Known Activations

terms related to fire extinguishing systems and their features

firefighting

mentions of firefighting or extinguishing — references to fires, firefighting personnel, equipment, systems, or actions to put fires out.

No Comments

No Known Activations