INDEX

Explanations

programming-related syntax or notation

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

Code or special characters

np_acts-logits-general · gemini-2.0-flash

contrast or pivot

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

InjectAttribute

-0.91

basicConfig

-0.84

webElementXpaths

-0.76

 AssemblyCulture

-0.73

↵

-0.68

SourceChecksum

-0.67

 Chwiliwch

-0.62

/**

-0.61

ponses

-0.54

verwijspagina

-0.54

POSITIVE LOGITS

Datuak

0.77

—

0.61

NOTE

0.60

 NOTE

0.58

НИМА

0.56

 Réponses

0.56

ществ

0.55

 thể

0.52

Example

0.50

gbc

0.50

Activations Density 0.086%

programming-related syntax or notation

Code or special characters

contrast or pivot

No Comments

No Known Activations