INDEX

Explanations

phrases related to verification or validation checks

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

"Check" or "test" followed by a condition

np_acts-logits-general · gemini-2.0-flash

checking for validity or suitability

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 समीक्षक

-0.62

gatsby

-0.61

__*/

-0.55

TokenNameLBRACE

-0.54

 SEDS

-0.54

Tikang

-0.53

 HasFactory

-0.52

 насељу

-0.52

-------

-0.50

focusable

-0.50

POSITIVE LOGITS

 whether

0.97

whether

0.75

 validity

0.74

是否

0.71

 WHETHER

0.71

 suitability

0.68

 compatibility

0.67

 Whether

0.66

 apakah

0.65

 against

0.63

Activations Density 0.325%

phrases related to verification or validation checks

"Check" or "test" followed by a condition

checking for validity or suitability

No Comments

No Known Activations