INDEX

Explanations

JavaScript code snippets.

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

points in code related to mathematical operations or calculations.

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

mathematical functions and operations, particularly those related to trigonometry and geometry.

oai_token-act-pair · claude-3-5-sonnet-20240620 Triggered by @bot

Following periods and math/code related tokens

np_acts-logits-general · gemini-2.0-flash

police officer, test to

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

Geplaatst

-0.66

 lenker

-0.64

хьтан

-0.61

[:,

-0.54

mpä

-0.53

Obrázky

-0.53

PerformLayout

-0.52

 verme

-0.50

ItemLayout

-0.49

 ivelany

-0.48

POSITIVE LOGITS

enumi

0.65

ignty

0.63

存于互联网档案馆

0.61

pow

0.60



0.58

ustimmung

0.57

Skocz

0.55

Aktualisiert