INDEX

Explanations

technical, scientific and medical terminology, especially experimental procedures and related concepts

oai_token-act-pair · gemini-2.0-flash

the word 'as' in various languages

np_token-act-pair-logits · gpt-4o-mini

"as" in other languages

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Personendaten

-0.92

 виправивши

-0.88

 Signalez

-0.86

 Италијани

-0.80

 AssemblyCompany

-0.77

findpost

-0.77

 lenker

-0.76

GEBURTSDATUM

-0.75

 ujednoznacz

-0.72

 disambiguazione

-0.72

POSITIVE LOGITS

as

2.67

 sebagai

1.70

 как

1.44

sebagai

1.30

作为

1.30

as

1.28

 jako

1.28

作為

1.26

 ως

1.26

 як

1.23

Activations Density 5.521%

technical, scientific and medical terminology, especially experimental procedures and related concepts

the word 'as' in various languages

"as" in other languages

No Comments

No Known Activations