INDEX

Explanations

keywords and parameters commonly associated with programming and configuration files

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

before capitalized words

np_acts-logits-general · gemini-2.0-flash

programming library names

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

expandindo

-1.10

 kaarangay

-0.87

RegressionTest

-0.79

osoba

-0.78

 дописавши

-0.77

 betweenstory

-0.76

IVEREF

-0.74

انيف

-0.73

GEBURTSDATUM

-0.71

intios

-0.71

POSITIVE LOGITS

 BoxDecoration

0.79

bootstrapcdn

0.77

GraphicsUnit

0.73

ValueGeneration

0.73

ConstraintMaker

0.72

NOPQRST

0.71

LLocation

0.68

 InputDecoration

0.66

tagHelper

0.66

cdnjs

0.65

Activations Density 14.759%

keywords and parameters commonly associated with programming and configuration files

before capitalized words

programming library names

No Comments

No Known Activations