INDEX

Explanations

specific codes, acronyms, and data identifiers associated with research and technology contexts

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 صوتيه

-0.80

makeConstraints

-0.73

 propOrder

-0.67

Diwedd

-0.66

ьажоргаш

-0.66

 تضيفلها

-0.66

alakip

-0.66

PREFERRED

-0.66

devamını

-0.63

 čierna

-0.62

POSITIVE LOGITS

Autoritní

0.53

 jsonData

0.45

ML

0.43

RS

0.42

DL

0.42

DM

0.42

 RCMP

0.41

MS

0.41

DC

0.40

FC

0.40

Activations Density 0.759%

specific codes, acronyms, and data identifiers associated with research and technology contexts

No Comments

No Known Activations