INDEX

Explanations

names of individuals and entities related to music, visual art, and health organizations

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

Follows capitalized words or names

np_acts-logits-general · gemini-2.0-flash

places and institutions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

omeness

-0.49

ρον

-0.49

 chi̍t

-0.49

rony

-0.46

:].

-0.44

;';

-0.43

hoc

-0.43

σθαι

-0.43

+#+#

-0.42

 الحره

-0.42

POSITIVE LOGITS

SharedDtor

0.67

الدراسه

0.66

 mergeFrom

0.65

ของ

0.65

 belonging

0.64

 milik

0.64

来自

0.63

 của

0.62

 של

0.61

LayoutConstraint

0.61

Activations Density 0.601%

names of individuals and entities related to music, visual art, and health organizations

Follows capitalized words or names

places and institutions

No Comments

No Known Activations