INDEX

Explanations

terms related to entities in programming or data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

GEBURTSDATUM

-1.09

 élector

-0.79

 ISNI

-0.73

 فريبيس

-0.68

 beginnetje

-0.67

 صوتيه

-0.67

 tragé

-0.66

 архивлан

-0.65

WebServlet

-0.65

ímp

-0.65

POSITIVE LOGITS

entities

0.95

 agreed

0.85

Entities

0.84

ENTITY

0.81

 Entities

0.81

 entities

0.77

 agrees

0.74

mer

0.73

 agree

0.71

agreed

0.70

Activations Density 0.233%

terms related to entities in programming or data structures

No Comments

No Known Activations