INDEX

Explanations

patterns or sequences of numbers and symbols, particularly in a structured context like references or citations

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

Numbers following a parenthesis

np_acts-logits-general · gemini-2.0-flash

academic paper citations

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

:✨

-0.60

...</

-0.60

}}</

-0.56

帖最后由

-0.54

onghi

-0.51

__(/*!

-0.51

 <=",

-0.50

…~

-0.50

 оригіналу

-0.50

..."

-0.49

POSITIVE LOGITS

 Suppl

0.78

edn

0.66

TableHead

0.65

0.63

 internetowa

0.57

onAttach

0.56

Suppl

0.54

0.53

}(

0.53

Activations Density 0.286%

patterns or sequences of numbers and symbols, particularly in a structured context like references or citations

Numbers following a parenthesis

academic paper citations

No Comments

No Known Activations