INDEX

Explanations

references to programming code or technical parameters

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

Tokens after URLs or links

np_acts-logits-general · gemini-2.0-flash

`.com` domain links

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 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

Diwedd

-0.68

Izvori

-0.58

Personensuche

-0.53

 financeiro

-0.50

batore

-0.50

Referencie

-0.50

PMailer

-0.49

SaveChangesAsync

-0.47

sbericht

-0.47

ดง

-0.47

POSITIVE LOGITS

 ***!

0.50

 surla

0.46

GOTREF

0.44

Cer

0.43

Obrázky

0.42

NameInMap

0.41

(!__

0.40

 Henry

0.39

✨:

0.38

www

0.36

Activations Density 0.344%

references to programming code or technical parameters

Tokens after URLs or links

`.com` domain links

No Comments

No Known Activations