INDEX

Explanations

elements related to user interface design and functionality

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

icon stands for

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

ViewFeatures

-0.55

mappedBy

-0.51

stateMutability

-0.50

lapsingToolbar

-0.48

rajz

-0.48

StandardCharsets

-0.48

expandindo

-0.48

enderror

-0.47

 cuivre

-0.47

Geplaatst

-0.47

POSITIVE LOGITS

 software

0.42

software

0.41

 computer

0.38

autogui

0.36

kw

0.36

URIComponent

0.36

 kutu

0.35

Software

0.35

ècie

0.35

izoen

0.34

Activations Density 0.311%

elements related to user interface design and functionality

icon stands for

No Comments

No Known Activations