INDEX

Explanations

annotations related to class and method definitions in code

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

Annotation-related terms preceded by "@"

np_acts-logits-general · gemini-2.0-flash

@ annotations

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

providedIn

-0.59

imp

-0.58

-0.57

im

-0.57

-0.56

-0.55

 dual

-0.53

 that

-0.53

-0.52

imp

-0.52

POSITIVE LOGITS

IsMutable

0.77

AddTagHelper

0.76

 greateſt

0.75

 myſelf

0.74

 Shakspeare

0.72

 whereof

0.70

 itſelf

0.69

AddHtmlAttribute

0.69

 ―――――

0.69

存于互联网档案馆

0.69

Activations Density 0.020%

annotations related to class and method definitions in code

Annotation-related terms preceded by "@"

@ annotations

No Comments

No Known Activations