INDEX

Explanations

whitespace characters or spaces in the text

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

Prepositions or lowercase words preceding technical terms or variables

np_acts-logits-general · gemini-2.0-flash

at diagnosis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

WriteBarrier

-0.84

AccessorTable

-0.75

 CanadaChoose

-0.61

"")

-0.58

 Roskov

-0.56

ViewFeatures

-0.55

"")

-0.55

 nakalista

-0.55

PreferredItem

-0.54

saraba

-0.53

POSITIVE LOGITS

 становника

0.63

 Catalana

0.58

homonymie

0.58

testid

0.53

 inex

0.52

 ControllerBase

0.49

 intptr

0.48

hold

0.48

IsMutable

0.48

 HasFactory

0.47

Activations Density 0.088%

whitespace characters or spaces in the text

Prepositions or lowercase words preceding technical terms or variables

at diagnosis

No Comments

No Known Activations