INDEX

Explanations

occurrences of data manipulation and configuration-related terminology

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

Code snippets and data structures

np_acts-logits-general · gemini-2.0-flash

data assignment or destructuring

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 VIDEOTAPE

-0.53

👇

-0.51

 BeautifulSoup

-0.49

 Kessler

-0.47

newList

-0.47

AnimationsModule

-0.47

onViewCreated

-0.47

Kaieteur

-0.46

uVar

-0.44

 tqdm

-0.43

POSITIVE LOGITS

 utafitiHapana

0.81

>{@

0.72

/**

0.69

oa̍t

0.67

WebVitals

0.67

 sinned

0.66

 guste

0.65

 IBOutlet

0.65

Ashlee

0.64

NVIC

0.64

Activations Density 0.463%

occurrences of data manipulation and configuration-related terminology

Code snippets and data structures

data assignment or destructuring

No Comments

No Known Activations