INDEX

Explanations

statements explaining reasons or justifications

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

"is because" or a synonym

np_acts-logits-general · gemini-2.0-flash

reason why

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

IContainer

-0.72

argout

-0.69

EndProject

-0.65

bootstrapcdn

-0.61

findpost

-0.61

NameInMap

-0.59

 transférez

-0.58

 resourceCulture

-0.57

 itſelf

-0.57

getSeconds

-0.57

POSITIVE LOGITS

 because

2.66

because

2.26

Because

2.07

 Because

2.05

 porque

2.02

 BECAUSE

2.02

due

1.95

 karena

1.88

 потому

1.82

 debido

1.75

Activations Density 0.373%

statements explaining reasons or justifications

"is because" or a synonym

reason why

No Comments

No Known Activations