INDEX

Explanations

details about quantities and measurements in various contexts

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

Following the word "on"

np_acts-logits-general · gemini-2.0-flash

on followed by context

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

tanleria

-0.50

coroutines

-0.45

 terdekat

-0.44

 continúas

-0.43

 Vordergrund

-0.43

sphin

-0.41

Atsauces

-0.40

detectChanges

-0.39

RegressionTest

-0.39

 nemlig

-0.38

POSITIVE LOGITS

 ועל

0.63

 روی

0.61

 وعلى

0.61

onAdd

0.59

 Numerade

0.56

 platforms

0.55

onSearch

0.54

onCancel

0.52

 onCancelled

0.51

 island

0.51

Activations Density 0.545%

details about quantities and measurements in various contexts

Following the word "on"

on followed by context

No Comments

No Known Activations