INDEX

Explanations

medical and biological terms related to cellular functions and conditions, particularly in the context of injury and healing processes

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

organ/tissue/condition names

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

map

-0.27

 removed

-0.27

bas

-0.26

 Affiliations

-0.25

guy

-0.25

gridLayout

-0.25

 Appendix

-0.24

 мол

-0.24

gu

-0.24

comments

-0.23

POSITIVE LOGITS

 increí

0.71

󠁢

0.69

 pleaſure

0.68

出版年

0.63

 indígen

0.62

potranspiration

0.61

 estadounid

0.60

 Perſ

0.59

 leſs

0.59

 dieſe

0.58

Activations Density 1.572%

medical and biological terms related to cellular functions and conditions, particularly in the context of injury and healing processes

organ/tissue/condition names

No Comments

No Known Activations