INDEX

Explanations

terms that indicate suitability or appropriateness in various contexts

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

preceding "for," "if," or list-related terms

np_acts-logits-general · gemini-2.0-flash

appropriate or suitable for

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

hrter

-0.59

 AssemblyCompany

-0.55

anglès

-0.54

NavController

-0.52

 ExecuteAsync

-0.52

ISupport

-0.51

 createSlice

-0.50

 AssemblyCulture

-0.49

 protoimpl

-0.49

 autorytatywna

-0.47

POSITIVE LOGITS

 sized

0.99

 circonstances

0.83

Código

0.77

 Zeitpunkt

0.72

 estekak

0.69

mately

0.69

sized

0.68

 Proper

0.67

 réponse

0.66

APOLIS

0.64

Activations Density 0.337%

terms that indicate suitability or appropriateness in various contexts

preceding "for," "if," or list-related terms

appropriate or suitable for

No Comments

No Known Activations