INDEX

Explanations

programming terminology and references related to state management and options in code

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

code with state, priv, r

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

WriteTagHelper

-0.90

 betweenstory

-0.84

 Мексичка

-0.83

expandindo

-0.70

transQ

-0.62

 سكانية

-0.62

 AssemblyTitle

-0.60

 Roskov

-0.57

 ویکی‌پدی

-0.56

Portail

-0.55

POSITIVE LOGITS

entie

0.40

 though

0.40

ServletException

0.39

jsxFileName

0.37

 reduces

0.37

occasione

0.36

 Gewinn

0.36

文中

0.36

стях

0.36

 Histories

0.35

Activations Density 0.016%

programming terminology and references related to state management and options in code

code with state, priv, r

No Comments

No Known Activations