INDEX

Explanations

mathematical expressions and notations

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

"^{" followed by degree symbols or numbers

np_acts-logits-general · gemini-2.0-flash

degrees and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 Signalez

-0.85

dafx

-0.77

StoryboardSegue

-0.76

esez

-0.68

 calendriers

-0.66

didSet

-0.66

IBOutlet

-0.66

ecap

-0.64

Попис

-0.61

AndEndTag

-0.61

POSITIVE LOGITS

 disponibilités

0.57

ఠ

0.55

selho

0.53

tschafts

0.51

annica

0.49

ParallelGroup

0.49

Profes

0.49

WEBPACK

0.48

 Coney

0.46

tvguidetime

0.46

Activations Density 0.191%

mathematical expressions and notations

"^{" followed by degree symbols or numbers

degrees and measurements

No Comments

No Known Activations