INDEX

Explanations

URLs and references to online platforms

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

YouTube video links

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 ſche

-0.67

transQ

-0.66

 ſtate

-0.64

 ſta

-0.59

 juſ

-0.59

ſelf

-0.58

 houſe

-0.58

 ftate

-0.56

 faſt

-0.56

 pleaſure

-0.56

POSITIVE LOGITS

youtu

0.45

Video

0.44

 video

0.44

 clipped

0.42

YouTube

0.42

 YouTube

0.41

 clip

0.40

 vidéo

0.40

Vaata

0.39

Thank

0.39

Activations Density 0.002%

URLs and references to online platforms

YouTube video links

No Comments

No Known Activations