INDEX

Explanations

technical specifications and features related to software and application performance

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

new features or functionality

np_acts-logits-general · gemini-2.0-flash

features and functionality

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

 Italijanski

-0.71

SPATH

-0.65

ViewImports

-0.63

änden

-0.56

 rechange

-0.54

نسي

-0.53

EndInit

-0.52

GetAxis

-0.51

 ModelExpression

-0.51

IVEREF

-0.50

POSITIVE LOGITS

 features

2.23

 feature

1.93

 Features

1.91

features

1.90

Features

1.77

 FEATURES

1.70

feature

1.61

FEATURES

1.58

 Feature

1.57

Feature

1.51

Activations Density 0.403%

technical specifications and features related to software and application performance

new features or functionality

features and functionality

No Comments

No Known Activations