INDEX

Explanations

references to network-related concepts and terminology

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

after "network"

np_acts-logits-general · gemini-2.0-flash

network infrastructure

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyCompany

-0.67

GLS

-0.66

Tzu

-0.66

ddots

-0.65

 createSlice

-0.64

 écl

-0.64

runApp

-0.63

+#+

-0.62

HOLDER

-0.61

 Prid

-0.61

POSITIVE LOGITS

 networks

0.76

 Networks

0.64

networks

0.62

ers

0.62

Networks

0.57

dAtA

0.57

openConnection

0.53

 network

0.53

__((

0.52

 memer

0.52

Activations Density 0.128%

references to network-related concepts and terminology

after "network"

network infrastructure

No Comments

No Known Activations