INDEX

Explanations

historical context and events related to political figures or organizations

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

recent past and roles

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

top

-0.38

ロウ

-0.37

-0.36

"""

-0.35

pri

-0.33

 cool

-0.33

 useEffect

-0.33

 Toro

-0.32

ga

-0.31

POSITIVE LOGITS

 ſind

0.73

niſſe

0.71

DockStyle

0.68

 queſta

0.68

principalTable

0.67

 fashiola

0.65

$_(

0.65

Spoljašnje

0.64

bootstrapcdn

0.63

 '\\;'

0.63

Activations Density 0.018%

historical context and events related to political figures or organizations

recent past and roles

No Comments

No Known Activations