INDEX

Explanations

references to notable publications and authors

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

after punctuation in book/publication contexts

np_acts-logits-general · gemini-2.0-flash

authors and publishers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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



-0.61

日閲覧

-0.60

ionView

-0.58

'{@

-0.57

">—

-0.56

 onBind

-0.55

="@+

-0.53

giaan

-0.52

มาะ

-0.52

 bezeichneter

-0.52

POSITIVE LOGITS

 Random

0.70

Random

0.68

 publisher

0.66

 publishing

0.61

 Harper

0.61

random

0.59

 Penguin

0.59

 RANDOM

0.58

 published

0.58

published

0.57

Activations Density 0.137%

references to notable publications and authors

after punctuation in book/publication contexts

authors and publishers

No Comments

No Known Activations