INDEX

Explanations

mathematical expressions or terms related to functions and their properties

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

mathematical function notation F( )

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

</caption>

-0.52

StructEnd

-0.49

 potes

-0.49

PCell

-0.48

strum

-0.47

ActionEvent

-0.47

stateProvider

-0.46

 convo

-0.45

Hatch

-0.45

gridy

-0.45

POSITIVE LOGITS

uxxxx

0.79

 ajudá

0.57

 betweenstory

0.50

 afgelopen

0.49

 Autorisations

0.47

 própri

0.47

 vysok

0.47

 abenço

0.46

 mendatang

0.46

 avenir

0.46

Activations Density 0.060%

mathematical expressions or terms related to functions and their properties

mathematical function notation F( )

No Comments

No Known Activations