INDEX

Explanations

phrases that express disbelief or skepticism, often related to claims and statements

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

ending in "ing", "s", or "act"

np_acts-logits-general · gemini-2.0-flash

arising out of

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 autorytatywna

-0.89

SequentialGroup

-0.76

,:);

-0.75

migrationBuilder

-0.74

 AssemblyTitle

-0.69

 تانيه

-0.69

 Administrativna

-0.69

MemoryWarning

-0.69

Hauptartikel

-0.68

}")]

-0.67

POSITIVE LOGITS

 indeed

0.65

 inderdaad

0.62

AsUp

0.59

 appunto

0.58

 anything

0.57

 onOptions

0.57

 something

0.55

という言葉

0.54

“

0.53

Activations Density 0.629%

phrases that express disbelief or skepticism, often related to claims and statements

ending in "ing", "s", or "act"

arising out of

No Comments

No Known Activations