INDEX

Explanations

mentions of specific geographic locations or terms related to places and governance

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

cities, locations, and places

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

ValueStyle

-0.52

AppMethodBeat

-0.43

sockfd

-0.42

URLException

-0.41

Tampa

-0.41

 Tampa

-0.40

batore

-0.40

 pelota

-0.39

県

-0.39

 GetEnumerator

-0.38

POSITIVE LOGITS

 Delhi

1.08

Delhi

0.98

 दिल्ली

0.86

 delhi

0.85

 DELHI

0.73

 Beijing

0.68

 Moscow

0.66

 Gurgaon

0.63

 Moscú

0.61

 Noida

0.59

Activations Density 0.012%

mentions of specific geographic locations or terms related to places and governance

cities, locations, and places

No Comments

No Known Activations