INDEX

Explanations

specific terms that denote categories or titles in various contexts, such as artistic works, programming functions, or organizational structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Personendaten

-0.60

complexContent

-0.58

ConstraintMaker

-0.58

ReusableCell

-0.54

jenner

-0.54

ANCA

-0.49

mètre

-0.49

 casó

-0.49

 autorytatywna

-0.48

elcome

-0.48

POSITIVE LOGITS

 poffe

0.68

 snippetHide

0.61

 juſ

0.57

 ftate

0.57

 fuper

0.56

 Jefus

0.56

ंदीखरीदारी

0.55

 Theſe

0.54

 Diſ

0.54

 Majefty

0.54

Activations Density 0.132%

specific terms that denote categories or titles in various contexts, such as artistic works, programming functions, or organizational structures

No Comments

No Known Activations