INDEX

Explanations

references to data structures or components related to navigation within a user interface

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

Beginning of user input

np_acts-logits-general · gemini-2.0-flash

carousel slides

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

InitVars

-0.43

 refrigerator

-0.36

 StatelessWidget

-0.35

 actionMode

-0.35

fillRect

-0.33

 gren

-0.32

 Wiktionnaire

-0.32

 strade

-0.31

addHeader

-0.31

 trico

-0.31

POSITIVE LOGITS

 carousel

0.82

 slides

0.79

 slider

0.72

 Slider

0.71

 Slides

0.69

 slide

0.69

 Carousel

0.69

Carousel

0.68

Slider

0.66

 sliders

0.66

Activations Density 0.057%

references to data structures or components related to navigation within a user interface

Beginning of user input

carousel slides

No Comments

No Known Activations