INDEX

Explanations

phrases indicating requests for information or inquiries

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

Information, details, or further explanation following "for"

np_acts-logits-general · gemini-2.0-flash

for more details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 resourceCulture

-0.90

 <=",

-0.80

 فريبيس

-0.72

HasForeignKey

-0.67



-0.65

AsUp

-0.64

السكان

-0.64

省市镇

-0.64

WebServlet

-0.63

ControllerAdvice

-0.63

POSITIVE LOGITS

 details

0.94

 full

0.92

 complete

0.87

 further

0.83

 latest

0.82

 detailed

0.80

 current

0.79

 updates

0.78

 more

0.77

詳しい

0.75

Activations Density 0.198%

phrases indicating requests for information or inquiries

Information, details, or further explanation following "for"

for more details

No Comments

No Known Activations