INDEX

Explanations

references to commands and tokens related to interactive API functionalities

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

Code-related tokens or special characters

np_acts-logits-general · gemini-2.0-flash

Discord bot commands

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

 BitmapFactory

-0.59

complexType

-0.53

MeasureSpec

-0.52

herin

-0.49

ineno

-0.49

jspx

-0.48

Naissance

-0.48

 exercised

-0.47

ColumnHeaders

-0.47

дото

-0.47

POSITIVE LOGITS

 Discord

0.99

bot

0.96

 discord

0.94

Bot

0.92

bot

0.85

discord

0.85

Discord

0.84

 channel

0.79

Bot

0.79

 chat

0.79

Activations Density 0.163%

references to commands and tokens related to interactive API functionalities

Code-related tokens or special characters

Discord bot commands

No Comments

No Known Activations