INDEX

Explanations

occurrences and variations of the word "name" and its derivatives in various contexts

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

people's names

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

 Royaume

-0.37

 policiers

-0.35

bundles

-0.35

 durumda

-0.34

 duração

-0.34

Préparation

-0.34

sessions

-0.34

retudo

-0.33

失礼

-0.33

vres

-0.33

POSITIVE LOGITS

 name

1.20

 names

1.09

 NAME

0.94

 NAMES

0.90

名字

0.89

 Names

0.88

name

0.88

 Name

0.87

Name

0.84

NAME

0.83

Activations Density 0.021%

occurrences and variations of the word "name" and its derivatives in various contexts

people's names

No Comments

No Known Activations