INDEX

Explanations

references to popular culture and media

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

invented, followed, influence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 autorytatywna

-0.64

PreInfinity

-0.62

AISSEE

-0.58

 leſs

-0.53

Diweddarwch

-0.53

PostInfinity

-0.52

 disambiguazione

-0.52

OGND

-0.50

 kaarangay

-0.50

MigrationBuilder

-0.48

POSITIVE LOGITS

+:+

0.36

 influence

0.31

 influential

0.30

Спољашње

0.30

Publica

0.29

Enllaces

0.28

Pranala

0.28

 >=",

0.28

InjectMocks

0.28

 followed

0.27

Activations Density 0.043%

references to popular culture and media

invented, followed, influence

No Comments

No Known Activations