INDEX

Explanations

the word 'gold' and names of people (Amber, Sofia, etc.)

oai_token-act-pair · gemini-2.0-flash

gold

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

 gold

-2.58

 Gold

-2.47

Gold

-2.34

gold

-2.28

 GOLD

-2.14

GOLD

-2.13

 golden

-2.02

 Golden

-1.87

Golden

-1.82

golden

-1.75

POSITIVE LOGITS

 EconPapers

0.89

 الحره

0.87

 aveug

0.85

Rhestr

0.82

Tembelea

0.79

TemporalType

0.79

Източници

0.79

出版年

0.78

 كومونز

0.77

InSection

0.77

Activations Density 5.804%

the word 'gold' and names of people (Amber, Sofia, etc.)

gold

No Comments

No Known Activations