INDEX

Explanations

words related to books or reading.

oai_token-act-pair · gemini-2.0-flash

excerpts with the word "read"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 writing

-1.62

 Writing

-1.51

 Write

-1.40

Writing

-1.38

writing

-1.38

 write

-1.38

write

-1.31

 WRITING

-1.31

 WRITE

-1.30

Write

-1.28

POSITIVE LOGITS

 lido

0.49

 proč

0.46

 قر

0.44

 letti

0.43

 letto

0.41

per

0.39

lu

0.38

rea

0.38

lue

0.37

 לק

0.36

Activations Density 1.435%

words related to books or reading.

excerpts with the word "read"

No Comments

No Known Activations