INDEX

Explanations

keywords related to biological concepts and molecular processes

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

preceding "by"

np_acts-logits-general · gemini-2.0-flash

biological and technical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

geries

-0.61

weil

-0.59

 SwitchCompat

-0.58

 Ause

-0.57

 Tenden

-0.56

 Мексичка

-0.56

ishly

-0.56

AsUp

-0.56

 Godt

-0.55

 Avent

-0.55

POSITIVE LOGITS

 occurred

1.03

 oleh

0.98

 occurs

0.97

 avven

0.97

 dilakukan

0.96

 avviene

0.95

by

0.94

 către

0.93

 توسط

0.85

 occured

0.82

Activations Density 1.221%

keywords related to biological concepts and molecular processes

preceding "by"

biological and technical terms

No Comments

No Known Activations