INDEX

Explanations

articles preceding words related to beginnings or important events

oai_token-act-pair · gemini-2.0-flash

the

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

:✨

-0.96

homonymie

-0.94

Personensuche

-0.88

 виправивши

-0.87

 igång

-0.84

tvguidetime

-0.82

 Vikipedi

-0.75

adpleegd

-0.75

 jScrollPane

-0.73

utilisons

-0.73

POSITIVE LOGITS

<bos>

0.72

0.52

0.48

 pass

0.47

 times

0.47

0.46

0.45

Activations Density 2.738%

articles preceding words related to beginnings or important events

the

No Comments

No Known Activations