INDEX

Explanations

references to programming constructs and algorithms related to data structures and bounds

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

code structures and types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 utafitiHapana

-0.64

期刊论文

-0.54

Хьажоргаш

-0.54

Tembelea

-0.51

PointerException

-0.49

Toronto

-0.49

ReusableCell

-0.48

SourceChecksum

-0.48

adina

-0.46

mountable

-0.46

POSITIVE LOGITS

:✨

0.54

Demografie

0.34

 approach

0.34

 Approach

0.33

Espèce

0.33

>*/

0.31

PullParser

0.30

wapV

0.30

useEffect

0.30

dil

0.30

Activations Density 0.002%

references to programming constructs and algorithms related to data structures and bounds

code structures and types

No Comments

No Known Activations