INDEX

Explanations

elements related to technical documentation and configuration settings

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

GitHub repositories or issues

np_acts-logits-general · gemini-2.0-flash

GitHub repositories and programming discussions

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

GraphicsUnit

-0.77

XmlAccessType

-0.60

 Reſ

-0.56

XmlType

-0.56

 ſtate

-0.55

Xna

-0.54

 Archivado

-0.53

 uſed

-0.53

 dreamstime

-0.52

 houſe

-0.52

POSITIVE LOGITS

 GitHub

0.92

 Github

0.86

 github

0.81

 repo

0.79

Github

0.74

GitHub

0.73

 README

0.72

 demo

0.71

 Gatsby

0.69

 https

0.68

Activations Density 1.467%

elements related to technical documentation and configuration settings

GitHub repositories or issues

GitHub repositories and programming discussions

No Comments

No Known Activations