INDEX

Explanations

elements indicative of class declarations and definitions in programming

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

Class declarations

np_acts-logits-general · gemini-2.0-flash

`private` declarations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

enderror

-0.65

 通販

-0.58

+:+

-0.55

 formales

-0.54

libft

-0.51

Vortex

-0.51

aarrggbb

-0.50

 vocales

-0.50

znej

-0.50

DockStyle

-0.50

POSITIVE LOGITS

private

0.71

expandindo

0.64

 private

0.54

 wachten

0.53

JpaRepository

0.51

 voetballer

0.50

InjectAttribute

0.50

 Private

0.49

0.48

Activations Density 0.015%

elements indicative of class declarations and definitions in programming

Class declarations

`private` declarations

No Comments

No Known Activations