INDEX

Explanations

references to specific religious or mythological figures and practices

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

Followed by punctuation or capitalization

np_acts-logits-general · gemini-2.0-flash

mythological and historical figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

ไหน

-0.51

eroll

-0.50

 Central

-0.50

jewództ

-0.50

ARDO

-0.49

Artículo

-0.49

 mood

-0.49

interact

-0.48

に応

-0.48

POSITIVE LOGITS

 MainAxisSize

0.81

 couverte

0.65

ArrowToggle

0.53

 émissions

0.52

 TextAppearance

0.51

PhysRevLett

0.50

 embreagem

0.50

 faudrait

0.50

onAttach

0.49

 láser

0.49

Activations Density 0.345%

references to specific religious or mythological figures and practices

Followed by punctuation or capitalization

mythological and historical figures

No Comments

No Known Activations