INDEX

Explanations

fields related to metadata and descriptions in documents

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

structured descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

تقاوى

-0.74

transQ

-0.59

ыгана

-0.58

oredCriteria

-0.57

tagHelperRunner

-0.57

mobileqq

-0.57

ImageContext

-0.56

*/),

-0.54

abestanden

-0.54

XtraReports

-0.53

POSITIVE LOGITS

description

0.55

 descripción

0.47

 description

0.46

 descrição

0.43

 arcilla

0.42

 mourir

0.41

 describir

0.40

 almendras

0.40

 nutrición

0.38

Description

0.38

Activations Density 0.003%

fields related to metadata and descriptions in documents

structured descriptions

No Comments

No Known Activations