INDEX

Explanations

coding references and terminology related to application structure and components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

TagMode

-0.82

Према

-0.61

wpi

-0.57

SPATH

-0.55

UserScript

-0.54

ObservableList

-0.54



-0.54

MeasureSpec

-0.53

HasAnnotation

-0.52

parsedMessage

-0.52

POSITIVE LOGITS

 code

0.67

 coding

0.60

󠁮

0.60

 snippets

0.59

 inclusions

0.57

 CODE

0.57

 Code

0.57

 ویکی‌پدیا

0.56

代码

0.56

Code

0.54

Activations Density 0.970%

coding references and terminology related to application structure and components

No Comments

No Known Activations