INDEX

Explanations

technical and categorical terms related to systems or data structures

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

Text following numbers or symbols

np_acts-logits-general · gemini-2.0-flash

system configuration and transport

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

InvalidProtocol

-0.76

[])

-0.63

eneuve

-0.58

ViewFeatures

-0.58

uacute

-0.55

Gizmos

-0.55

)?;

-0.55

 mourut

-0.55



-0.54

()");

-0.54

POSITIVE LOGITS

AnimationsModule

0.73

Portail

0.70

verwijspagina

0.68

IntoConstraints

0.66

Hentet

0.65

addCriterion

0.62

Hozzáférés

0.59

<bos>

0.59

حياتها

0.56

 AssemblyCompany

0.56

Activations Density 1.730%

technical and categorical terms related to systems or data structures

Text following numbers or symbols

system configuration and transport

No Comments

No Known Activations