INDEX

Explanations

references to notable individuals or works in popular culture

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

following "the" that describe something

np_acts-logits-general · gemini-2.0-flash

the followed by adjectives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

SharedDtor

-0.81

 BoxDecoration

-0.73

"}>

-0.65

saraba

-0.65

()}>

-0.61

 snippetHide

-0.61

 doInBackground

-0.60

 оригіналу

-0.60

 onOptions

-0.59

ngOnInit

-0.58

POSITIVE LOGITS

 equally

0.92

 aptly

0.91

 infamous

0.88

 highly

0.84

 famously

0.83

 aforementioned

0.82

 recently

0.82

 famous

0.80

 wonderfully

0.80

 notorious

0.79

Activations Density 0.278%

references to notable individuals or works in popular culture

following "the" that describe something

the followed by adjectives

No Comments

No Known Activations