INDEX

Explanations

elements indicating quality and classification in various contexts

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

after hyphenated words

np_acts-logits-general · gemini-2.0-flash

scale, study, winning

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 Bewußt

-0.61

 enfans

-0.54

 InputDecoration

-0.54

ulongan

-0.52

 BoxDecoration

-0.52

DockStyle

-0.51

ungkin

-0.50

Ligações

-0.48

 navidad

-0.48

 ostavi

-0.48

POSITIVE LOGITS

первых

0.55

 menuItem

0.50

zzleHttp

0.48

 deleteById

0.47

՝

0.44

based

0.44

0.43

 Gigi

0.42

endswith

0.42

 vitt

0.41

Activations Density 0.597%

elements indicating quality and classification in various contexts

after hyphenated words

scale, study, winning

No Comments

No Known Activations