INDEX

Explanations

references to digital object identifiers (DOIs) related to academic publications

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

doi.org links

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 exponer

-0.46

 Trotz

-0.45

latter

-0.44

 exposição

-0.43

writeInt

-0.43

 lentejuelas

-0.43

 orientação

-0.43

 estatal

-0.43

 trovi

-0.43

 logiciels

-0.42

POSITIVE LOGITS

feira

0.93

 NSFW

0.84

dx

0.82

FontStyle

0.75

 Shutterstock

0.72

 الأصل

0.70

Shutterstock

0.56

dx

0.55

 noDo

0.54

########.

0.54

Activations Density 0.003%

references to digital object identifiers (DOIs) related to academic publications

doi.org links

No Comments

No Known Activations