INDEX

Explanations

phrases that indicate complexity or additional layers of meaning in a discussion

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

more than

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

 مرئيه

-0.47

 ویکی‌پدیای

-0.46

!")

-0.46

hyrchwyd

-0.44

ismet

-0.44

}]

-0.43

**/

-0.43

 الي

-0.40

ItemBackground

-0.40

点此举报

-0.40

POSITIVE LOGITS

beyond

0.53

StoryboardSegue

0.52

 deeper

0.52

 Beyond

0.52

 beyond

0.52

 than

0.49

Beyond

0.48

 BEYOND

0.47

 allá

0.46

worse

0.46

Activations Density 0.032%

phrases that indicate complexity or additional layers of meaning in a discussion

more than

No Comments

No Known Activations