INDEX

Explanations

specific terms and identifiers related to programming or coding elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

verwijspagina

-0.84

 يتيمه

-0.75

ⓘ

-0.73

 المعيارى

-0.73

DeleteBehavior

-0.73



-0.70

Personensuche

-0.70

########.

-0.70

曖昧さ回避

-0.69

runApp

-0.69

POSITIVE LOGITS

contentInset

0.49

__',

0.45

 beginnetje

0.45

拍

0.44

LookAnd

0.42

 subido

0.40

aarrggbb

0.39

 dátum

0.39

inquiry

0.39

 spørs

0.39

Activations Density 0.060%

specific terms and identifiers related to programming or coding elements

No Comments

No Known Activations