INDEX

Explanations

variable declarations and index variables in programming code

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

loop index `i`

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

Portale

-0.49

 '\\;'

-0.48

 unicornio

-0.47

 corações

-0.47

 jongen

-0.47

 moradores

-0.46

Portail

-0.46

 betrek

-0.45

 سكانية

-0.44

 kapturem

-0.44

POSITIVE LOGITS

ChildScrollView

0.64

sidemargin

0.59

webElementXpaths

0.57

 ujednoznacz

0.50

 disambiguazione

0.49

ReusableCell

0.46

errHandler

0.43

 indisponible

0.43

jsdelivr

0.41

openConnection

0.40

Activations Density 0.018%

variable declarations and index variables in programming code

loop index `i`

No Comments

No Known Activations