INDEX

Explanations

multiple spaces, or rows of periods as separators

oai_token-act-pair · gemini-2.0-flash

special characters or non-English tokens

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

technical experiment description

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.55

-0.50

-0.48

uya

-0.44

-0.43

-0.42

특

-0.42

She

-0.41

in

-0.41

zzer

-0.40

POSITIVE LOGITS

 صوتيه

0.94

rungsseite

0.92

 préfé

0.81

 дописавши

0.80

 houſe

0.80

 resourceCulture

0.78

 يتيمه

0.78

 חיצוניים

0.78

 disponibilités

0.75

 فريبيس

0.74

Activations Density 2.020%

multiple spaces, or rows of periods as separators

special characters or non-English tokens

technical experiment description

No Comments

No Known Activations