INDEX

Explanations

references to dot notation, specifically related to programming or data representation

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

"Dot" or related variations

np_acts-logits-general · gemini-2.0-flash

dot, dot plots, dot product

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

MigrationBuilder

-0.67

CDCl

-0.65

#+#

-0.64

 oppervlak

-0.58

はじめに

-0.56

uxxxx

-0.55

 Erzb

-0.54

 lemn

-0.53

uchtung

-0.51

 Guido

-0.51

POSITIVE LOGITS

Dot

1.11

dot

1.10

dot

0.98

Dot

0.94

 Dots

0.94

 dots

0.88

DOT

0.86

Dots

0.78

dots

0.73

 ドット

0.73

Activations Density 0.188%

references to dot notation, specifically related to programming or data representation

"Dot" or related variations

dot, dot plots, dot product

No Comments

No Known Activations