INDEX

Explanations

blocks of code and programming concepts

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

Code, especially in Java or Python

np_acts-logits-general · gemini-2.0-flash

energy unit eV

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

 виправивши

-0.69

Dữ

-0.65

 كومونز

-0.62

Controllo

-0.62

 <<<<<<<<<<<<<<

-0.61

StoryboardSegue

-0.60

nestjs

-0.60

 ligiloj

-0.59

jgl

-0.55

MathML

-0.55

POSITIVE LOGITS

 zelve

0.61

 PLWABN

0.56

 else

0.53

спеди

0.52

 Mercier

0.52

 judiciales

0.51

 '\\;'

0.49

 publicitaires

0.49

 tidligere

0.49

 préfé

0.47

Activations Density 0.048%

blocks of code and programming concepts

Code, especially in Java or Python

energy unit eV

No Comments

No Known Activations