INDEX

Explanations

references to the quantity or value of something

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

"How much" questions

np_acts-logits-general · gemini-2.0-flash

how much

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 suficientemente

-0.56

 sufficiently

-0.54

 viewDidLoad

-0.54

//

-0.53

actionMode

-0.51

 suffisamment

-0.51

 pakan

-0.50

LookAnd

-0.50

[]:

-0.49

CrossRef

-0.49

POSITIVE LOGITS

 money

0.91

 effort

0.83

########.

0.80

 information

0.75

 emphasis

0.75

 time

0.75

 времени

0.75

 attention

0.74

 exposure

0.73

 influence

0.71

Activations Density 0.215%

references to the quantity or value of something

"How much" questions

how much

No Comments

No Known Activations