INDEX

Explanations

words related to people's attitudes, beliefs, or expectations.

oai_token-act-pair · gemini-2.0-flash

thoughts/beliefs

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/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.4.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

تقاوى

-0.81

KURZBESCHREIBUNG

-0.77

 AssemblyCompany

-0.71

CloseOperation

-0.71

\{\\

-0.70

 Chwiliwch

-0.67

enumi

-0.66

ConstraintMaker

-0.65

 تضيفلها

-0.65

 CreateTagHelper

-0.65

POSITIVE LOGITS

<bos>

0.87

日閲覧

0.49

endphp

0.48

bag

0.42

 {}));

0.42

 Khas

0.42

Spoljašnje

0.42

횟

0.41

kloped

0.40

setAuto

0.39

Activations Density 2.843%

words related to people's attitudes, beliefs, or expectations.

thoughts/beliefs

No Comments

No Known Activations