INDEX

Explanations

questions and inquiries about specific topics

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

asking what something is

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

endregion

-0.58

のかもしれません

-0.52

 rowIndex

-0.51

esterno

-0.51

autogui

-0.50

 Lari

-0.48

enetrable

-0.48

sbericht

-0.47

 columnIndex

-0.47

پیوند

-0.47

POSITIVE LOGITS

 what

1.79

what

1.60

What

1.52

 What

1.39

 WHAT

1.37

WHAT

1.31

 whats

0.94

whats

0.91

hva

0.81

Hva

0.80

Activations Density 0.076%

questions and inquiries about specific topics

asking what something is

No Comments

No Known Activations

questions and inquiries about specific topics

asking what something is

No Comments

No Known Activations