INDEX

Explanations

when things were invented or discovered

oai_token-act-pair · gemini-2.0-flash

Inventions and discoveries

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

 years

-0.57

 early

-0.57

 năm

-0.56

 año

-0.55

Năm

-0.55

 year

-0.54

 awal

-0.52

 Years

-0.51

 Jahr

-0.50

Begriffsklä

-0.50

POSITIVE LOGITS

 ſeveral

0.94

 myſelf

0.88

 Theſe

0.88

 pleaſure

0.87

 fubject

0.85

Efq

0.85

 Majefty

0.84

oredCriteria

0.84

 houſe

0.84

 occaf

0.83

Activations Density 2.574%

when things were invented or discovered

Inventions and discoveries

No Comments

No Known Activations