INDEX

Explanations

programming interfaces and listeners in code

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

event listener binding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ModelExpression

-0.98

 للاسماء

-0.90

AddTagHelper

-0.84

httphttps

-0.81

ConstraintMaker

-0.79

########.

-0.79

 CreateTagHelper

-0.78

lapsingToolbar

-0.77

 queſta

-0.76

HasAnnotation

-0.76

POSITIVE LOGITS

ViewFeatures

0.42

 portavoz

0.25

 ActionListener

0.24

kym

0.23

err

0.21

 Económica

0.20

 tarko

0.20

 näytte

0.20

 financiera

0.20

test

0.20

Activations Density 0.002%

programming interfaces and listeners in code

event listener binding

No Comments

No Known Activations