INDEX

Explanations

specific variables and terms related to data analysis and programming structures

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

Abbreviations and short codes

np_acts-logits-general · gemini-2.0-flash

acronyms and specific nouns

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

Portail

-0.91

NameInMap

-0.88

 ddelweddau

-0.84

protoimpl

-0.83

 समीक्षाओं

-0.82

 Roskov

-0.81

出版年

-0.78

AsUp

-0.76

tagHelperRunner

-0.75

 GenerationType

-0.74

POSITIVE LOGITS

 उत्त

0.36

 NSCoder

0.35

 domanda

0.34

and

0.33

ۜ

0.33

Trainer

0.32

AndView

0.32

と言っても

0.32

 ожи

0.31

ợn

0.31

Activations Density 0.907%

specific variables and terms related to data analysis and programming structures

Abbreviations and short codes

acronyms and specific nouns

No Comments

No Known Activations