INDEX

Explanations

occurrences of the term "keywords" and related metadata in documents

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 surla

-0.46

rup

-0.42

DialogContent

-0.42

 stopped

-0.40

Наводи

-0.40

liptic

-0.39

Ծանոթ

-0.39

oldt

-0.38

 tempor

-0.38

sla

-0.38

POSITIVE LOGITS

 keywords

0.79

KEYWORDS

0.70

Keywords

0.67

keywords

0.66

 Keywords

0.65

Personendaten

0.61

关键词

0.60

AccessorTable

0.59

 AssemblyCulture

0.56

 chiave

0.52

Activations Density 0.005%

occurrences of the term "keywords" and related metadata in documents

No Comments

No Known Activations