INDEX

Explanations

markup or code elements related to links and image attributes

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

<start_of_turn>user

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

 يتيمه

-0.54

 wikipagina

-0.53

tanleria

-0.53

 propOrder

-0.52

NewUrlParser

-0.52

LayoutStyle

-0.52

epam

-0.51

apolis

-0.50

transQ

-0.50

şört

-0.49

POSITIVE LOGITS

favicon

0.40

 gezondheid

0.37

 medios

0.32

 imageNamed

0.31

exitRule

0.31

Drawn

0.31

 keuze

0.31

Recognition

0.30

 nemici

0.30

URLException

0.29

Activations Density 0.002%

markup or code elements related to links and image attributes

<start_of_turn>user

No Comments

No Known Activations