INDEX

Explanations

references to specific scientific and technical terms, particularly in relation to health and biology

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Butter

-0.48

 Malabar

-0.48

 phyto

-0.46

 lipo

-0.46

 Paddy

-0.45

躇

-0.45

ppi

-0.45

_("

-0.45

 Schro

-0.45

 Parac

-0.45

POSITIVE LOGITS

تقاوى

0.96

 protoimpl

0.80

 Мексичка

0.80

contentLoaded

0.79

 resourceCulture

0.75

LookAnd

0.74

 الرياضيه

0.74

 pinulongan

0.74

IsMutable

0.72

 ویکی‌پدیای

0.71

Activations Density 1.183%

references to specific scientific and technical terms, particularly in relation to health and biology

No Comments

No Known Activations