INDEX

Explanations

references to different geographic locations

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

geographical regions or areas

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

<bos>

-0.60

blut

-0.45

computation

-0.44

 investissements

-0.43

compute

-0.40

Buc

-0.40

 Spectroscopy

-0.39

 מו

-0.39

isContained

-0.39

instancetype

-0.39

POSITIVE LOGITS

 areas

1.54

 Areas

1.46

areas

1.37

Areas

1.35

 AREAS

1.21

 áreas

1.05

 områ

1.02

 Bereiche

0.91

 Bereichen

0.89

 regions

0.85

Activations Density 0.008%

references to different geographic locations

geographical regions or areas

No Comments

No Known Activations