INDEX

Explanations

terms related to separation or segmentation

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

divided by or into

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

/**

-0.48

-0.44

Efq

-0.42

lccn

-0.42

+:+

-0.42

httphttps

-0.42

waitKey

-0.41

PerformLayout

-0.41

 UserModel

-0.40

 NavController

-0.40

POSITIVE LOGITS

 split

0.84

 divided

0.74

 Split

0.70

 divide

0.70

 divides

0.67

 subdivided

0.65

 splits

0.65

 divisions

0.65

split

0.65

 splitting

0.64

Activations Density 0.049%

terms related to separation or segmentation

divided by or into

No Comments

No Known Activations