INDEX

Explanations

function calls and method executions in code

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

Code snippets with semicolons and parenthesis

np_acts-logits-general · gemini-2.0-flash

code structure delimiters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

ReusableCell

-0.72

transQ

-0.62

 itſelf

-0.60

extAlignment

-0.60

ſelves

-0.59

 eſſ

-0.57

 invokingState

-0.57

:✨

-0.56

httphttps

-0.56

 ſont

-0.54

POSITIVE LOGITS

EndInit

0.54

destroyAll

0.52

ResumeLayout

0.51

detectChanges

0.49

printStackTrace

0.49

GOTREF

0.48

moveToFirst

0.47

SaveChangesAsync

0.47

principalColumn

0.47

 typelib

0.44

Activations Density 0.349%

function calls and method executions in code

Code snippets with semicolons and parenthesis

code structure delimiters

No Comments

No Known Activations