INDEX

Explanations

references to locations, institutions, and notable entities

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

after titles/names and organization names

np_acts-logits-general · gemini-2.0-flash

organizations and entities

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

parsedMessage

-0.87

 tartalomajánló

-0.79

SharedCtor

-0.74

etheless

-0.69

发表于

-0.69

rungsseite

-0.69

:✨

-0.68

 تكبرها

-0.68

theless

-0.68

IsMutable

-0.65

POSITIVE LOGITS

 Service

0.81

 Club

0.75

 Company

0.74

 Center

0.72

 Party

0.72

 Group

0.71

 Society

0.69

™

0.68

 System

0.67

 School

0.66

Activations Density 1.091%

references to locations, institutions, and notable entities

after titles/names and organization names

organizations and entities

No Comments

No Known Activations