INDEX

Explanations

mentions of places or entities associated with "Fort," particularly in relation to locations or events

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

Fort followed by a place name

np_acts-logits-general · gemini-2.0-flash

Fort followed by a place name

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

pośred

-0.68

Demografia

-0.67

 Himo

-0.55

DoubleQuotes

-0.55

emiah

-0.53

!("{}",

-0.51

 préférences

-0.50

 ineligible

-0.49

iibo

-0.48

 étrangères

-0.48

POSITIVE LOGITS

 Worth

0.63

 Myers

0.59

 Bragg

0.58

ServletException

0.56

 '\\;'

0.55

 Lauderdale

0.55

blockList

0.54

Aholisi

0.54

 WORTH

0.53

Worth

0.53

Activations Density 0.107%

mentions of places or entities associated with "Fort," particularly in relation to locations or events

Fort followed by a place name

Fort followed by a place name

No Comments

No Known Activations