INDEX

Explanations

words and phrases that represent an opinion or judgement made about something.

oai_token-act-pair · gemini-2.0-flash

totally completely

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

GEBURTSDATUM

-0.96

 auroit

-0.87

IsContent

-0.87

 pouvoit

-0.85

 feroit

-0.84

 avoient

-0.84

 disambiguazione

-0.83

Personendaten

-0.82

 mourut

-0.81

 debout

-0.79

POSITIVE LOGITS

»

0.47

fe

0.42

Fe

0.42

ir

0.40

”

0.40

tz

0.40

hot

0.39

 rapid

0.39

 also

0.38

«

0.38

Activations Density 14.911%

words and phrases that represent an opinion or judgement made about something.

totally completely

No Comments

No Known Activations