INDEX

Explanations

details and metrics related to comparative analysis and evaluation in research contexts

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

"Each" followed by types or categories

np_acts-logits-general · gemini-2.0-flash

each category

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 onCreateView

-0.80

IGraphics

-0.50

rawDesc

-0.49

 mío

-0.47

 sanno

-0.44

 tewas

-0.43

 trasera

-0.43

 médica

-0.42

 Affaires

-0.42

ouk

-0.42

POSITIVE LOGITS

 category

1.30

 region

1.21

 species

1.19

 genre

1.11

 sector

1.05

 categories

1.04

 regions

0.99

 segment

0.99

 location

0.98

 type

0.97

Activations Density 1.337%

details and metrics related to comparative analysis and evaluation in research contexts

"Each" followed by types or categories

each category

No Comments

No Known Activations