INDEX

Explanations

questions and assertive statements clearly articulated in a structured manner

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

question starters

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

DockStyle

-0.46

帖最后由

-0.34

“

-0.33

Inoltre

-0.31

исленность

-0.31

 vnto

-0.31

Và

-0.31

}{{\

-0.30

evos

-0.30

zarchiwizowane

-0.29

POSITIVE LOGITS

 esternos

0.58

󠀠

0.58

 OFDb

0.57

 تضيفلها

0.54

ſammen

0.53

๫

0.51

 Biôgrafia

0.51

aimeJ

0.51

࿊

0.49

Ӕ

0.49

Activations Density 0.038%

questions and assertive statements clearly articulated in a structured manner

question starters

No Comments

No Known Activations