INDEX

Explanations

instances of the word "when."

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

starts with when

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ujednoznacz

-0.75

 aapt

-0.60

 HasFactory

-0.59

 IBOutlet

-0.57

 betweenstory

-0.54

ValueStyle

-0.52

elemField

-0.52

 становника

-0.50

rungsseite

-0.49

 Италијани

-0.49

POSITIVE LOGITS

When

0.73

 When

0.69

If

0.59

Whenever

0.56

 Když

0.55

 Quando

0.54

Quando

0.54

 Когда

0.54

 Lorsqu

0.53

If

0.52

Activations Density 0.037%

instances of the word "when."

starts with when

No Comments

No Known Activations