INDEX

Explanations

terms related to classification, specifications, and specific attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

MigrationBuilder

-0.65

KommentareTeilen

-0.64

 normaux

-0.64

 ordinaires

-0.63

DrawerToggle

-0.62

idalgo

-0.60

 AssemblyProduct

-0.59

 indépendante

-0.58

ibatis

-0.58

 geblieben

-0.58

POSITIVE LOGITS

 certain

0.89

 specific

0.82

 tertentu

0.78

特定的

0.76

certain

0.76

 bestimmte

0.73

 bestimmten

0.73

 Certain

0.73

特定

0.72

Certain

0.72

Activations Density 0.529%

terms related to classification, specifications, and specific attributes

No Comments

No Known Activations