INDEX

Explanations

references to disks or discs in various contexts

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

disk and its properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

Want

-0.53

ians

-0.48

expects

-0.46

Autres

-0.45

Цели

-0.44

 relatifs

-0.44

Leading

-0.43

hugh

-0.43

Tienen

-0.43

ต่าง

-0.43

POSITIVE LOGITS

 Disk

1.05

 disk

1.04

 disc

1.01

 Disc

0.99

Disk

0.95

disk

0.92

 disks

0.89

 discs

0.88

 DISC

0.84

Disc

0.84

Activations Density 0.008%

references to disks or discs in various contexts

disk and its properties

No Comments

No Known Activations