INDEX

Explanations

UI elements or indicators in a programming context

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

defining mathematical functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 Valerio

-0.51

sprozess

-0.50

webElementXpaths

-0.49

veur

-0.47

новниш

-0.47

 Daly

-0.46

 nostru

-0.46

ㅐ

-0.45

hman

-0.45

jména

-0.44

POSITIVE LOGITS

 BorderSide

0.68

 Icon

0.65

Icon

0.55

withId

0.49

CopyWith

0.48

 IconData

0.48

 InputDecoration

0.47

principalColumn

0.45

AlterField

0.45

@[+][

0.42

Activations Density 0.001%

UI elements or indicators in a programming context

defining mathematical functions

No Comments

No Known Activations