INDEX

Explanations

instances of significant actions or events that create an impact or transformation

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

preposition "to" sequences

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

 Pech

-0.42

fileID

-0.41

FDRE

-0.40

 Creighton

-0.40

FontAwesomeIcon

-0.38

resultList

-0.38

startX

-0.38

={<

-0.38

fileType

-0.37

BeginInit

-0.37

POSITIVE LOGITS

 vistazo

0.69

TextHelper

0.69

httphttps

0.68

bootstrapcdn

0.65

accès

0.65

pecto

0.64

accéder

0.64

subpackage

0.63

\,.

0.62

 fubject

0.62

Activations Density 0.749%

instances of significant actions or events that create an impact or transformation

preposition "to" sequences

No Comments

No Known Activations