INDEX

Explanations

occurrences of the word "name" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 kaynağından

-0.58

 Baillargeon

-0.56

MethodManager

-0.51

RectangleBorder

-0.51

ViewFeatures

-0.50

 ujednoznacz

-0.48

ScopeManager

-0.47

 BorderSide

-0.47

lementation

-0.47

windowFixed

-0.46

POSITIVE LOGITS

Name

1.35

 name

1.33

 Name

1.26

name

1.15

 NAME

0.98

NAME

0.89

 nome

0.80

Nombre

0.79

ByName

0.76

 autorytatywna

0.75

Activations Density 0.076%

occurrences of the word "name" in various contexts

No Comments

No Known Activations