INDEX

Explanations

guides and resources for practical tasks or instructions

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

Followed by article, here, below, or you

np_acts-logits-general · gemini-2.0-flash

content introduction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

bootstrapcdn

-0.81

twimg

-0.64

قليم

-0.59

WithIOException

-0.55

 resourceCulture

-0.54

GraphicsUnit

-0.53

 Lokales

-0.52

LookAnd

-0.51

 nights

-0.51

 Locally

-0.51

POSITIVE LOGITS

 below

0.83

 listed

0.71

 article

0.70

below

0.68

 artikel

0.68

 Below

0.68

 learn

0.67

 simak

0.66

 penjelasan

0.66

Below

0.66

Activations Density 0.139%

guides and resources for practical tasks or instructions

Followed by article, here, below, or you

content introduction

No Comments

No Known Activations