INDEX

Explanations

references to programming or mathematical syntax, particularly related to arrays and functions

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

LaTeX math expressions

np_acts-logits-general · gemini-2.0-flash

mathematical symbols and scientific names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

########.

-0.57

AutoScaleMode

-0.49

 &___

-0.45

endwhile

-0.44

AccessorTable

-0.43

ResumeLayout

-0.42

 виправивши

-0.42

AlterField

-0.42

PreferredItem

-0.40

LookAnd

-0.40

POSITIVE LOGITS

 EconPapers

0.66

mrow

0.62

MathML

0.52

transQ

0.48

 AssemblyProduct

0.47

FontOfSize

0.47

extAlignment

0.47

⟬

0.47

 мәкал

0.46

原始内容存档于

0.46

Activations Density 0.400%

references to programming or mathematical syntax, particularly related to arrays and functions

LaTeX math expressions

mathematical symbols and scientific names

No Comments

No Known Activations