INDEX

Explanations

technical terms and phrases related to neurophysiology and electrical property measurements in neurons

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

time and signal duration

np_acts-logits-general · gemini-2.0-flash

timing, duration, and decay

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

ору

-0.48

agaimana

-0.43

biome

-0.43

 rationality

-0.41

IFIC

-0.41

ficiency

-0.41

otent

-0.40

ISupport

-0.40

 favoritos

-0.39

getColumnIndex

-0.39

POSITIVE LOGITS

 duration

1.10

 time

1.07

 delay

0.98

 transient

0.96

 delayed

0.92

 timing

0.91

 decay

0.90

duration

0.90

 durations

0.89

 timed

0.89

Activations Density 1.722%

technical terms and phrases related to neurophysiology and electrical property measurements in neurons

time and signal duration

timing, duration, and decay

No Comments

No Known Activations