INDEX

Explanations

phrases that indicate conditional actions or functions related to key events

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

articles 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 @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

tagHelperRunner

-0.57

 للمعارف

-0.56

 things

-0.56

álisis

-0.54

 sand

-0.53

led

-0.51

帖最后由

-0.50

 שוליים

-0.50

Alone

-0.50

<!--[

-0.50

POSITIVE LOGITS

 resourceCulture

0.60

ContextHolder

0.59

EndInit

0.54

ogia

0.54

"];

0.54

 different

0.54

 majú

0.53

енча

0.53

"]));

0.52

ThemeOverlay

0.52

Activations Density 0.206%

phrases that indicate conditional actions or functions related to key events

articles followed by adjectives

No Comments

No Known Activations