INDEX

Explanations

specific numerical values and indicators in a medical or scientific context

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

abstract articles

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 disambiguazione

-0.66

 nahilalakip

-0.65

 '\\;'

-0.59

 pinulongan

-0.58

 bookId

-0.57

yarnpkg

-0.56

WriteTagHelper

-0.56

OGND

-0.56

 Qaraldi

-0.54

sizeCache

-0.54

POSITIVE LOGITS

 article

0.91

 abstract

0.81

abstract

0.77

 abstracts

0.75

 Abstract

0.73

article

0.71

Abstract

0.69

 abstracta

0.68

 artículo

0.66

 abstracto

0.65

Activations Density 0.083%

specific numerical values and indicators in a medical or scientific context

abstract articles

No Comments

No Known Activations