INDEX

Explanations

code snippets that include assignments and return statements

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

Code related to boolean values

np_acts-logits-general · gemini-2.0-flash

boolean return false

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

styleType

-0.64

]++;

-0.62

bootstrapcdn

-0.59

Chham

-0.58

)++;

-0.55

:✨

-0.55

)>=

-0.54

GraphicsUnit

-0.53

 Italijanski

-0.53

']>

-0.51

POSITIVE LOGITS

 false

2.22

false

1.99

 False

1.75

False

1.65

 FALSE

1.44

FALSE

1.28

 falso

1.14

 falsas

1.08

 falsos

1.08

 falsa

1.07

Activations Density 0.112%

code snippets that include assignments and return statements

Code related to boolean values

boolean return false

No Comments

No Known Activations