INDEX

Explanations

for loops, some other keywords, and punctuation in code

oai_token-act-pair · gemini-2.0-flash

representations of the number zero

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

=

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

windowFixed

-0.86

styleType

-0.85

bootstrapcdn

-0.85

+#+#

-0.84

Personensuche

-0.83

EDEFAULT

-0.83

 للاسماء

-0.79

 cherchés

-0.76

ViewFeatures

-0.74

 linkovi

-0.73

POSITIVE LOGITS

0.95

０

0.58

۰

0.43

𝟬

0.38

 isto

0.38

 zero

0.38

 isso

0.37

০

0.37

٠

0.36

Activations Density 3.847%

for loops, some other keywords, and punctuation in code

representations of the number zero

=

No Comments

No Known Activations