INDEX

Explanations

references to historical or mythical figures and their attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 समीक्षक

-0.59

 الرياضيه

-0.56

 arşivlendi

-0.55

ագրություններ

-0.55

Autoritní

-0.53

 itinéraires

-0.52

 للاسماء

-0.50

 surla

-0.50

 jsPsych

-0.50

Hentet

-0.49

POSITIVE LOGITS

 land

0.68

 wastes

0.62

 precincts

0.59

 Land

0.59

 lands

0.58

بوابة

0.57

Land

0.56

श्ले

0.55

 LAND

0.55

 patrie

0.55

Activations Density 0.292%

references to historical or mythical figures and their attributes

No Comments

No Known Activations