INDEX

Explanations

references to people, particularly authors and researchers in various fields

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

before people's last names

np_acts-logits-general · gemini-2.0-flash

Names with surnames

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

transQ

-0.56

 popoli

-0.52

 Sternen

-0.48

 Bohn

-0.48

 capuz

-0.47

 bordada

-0.47

 enfermed

-0.47

 Brandt

-0.47

Vanjske

-0.47

 indígen

-0.47

POSITIVE LOGITS

󠁢

0.46

UseVisualStyle

0.45

Bog

0.42

yyj

0.41

 Chid

0.41

 Cumber

0.40

PhysRevLett

0.40

 McCar

0.40

romyalgia

0.40

IMPORTED

0.40

Activations Density 1.500%

references to people, particularly authors and researchers in various fields

before people's last names

Names with surnames

No Comments

No Known Activations