INDEX

Explanations

statistics related to a competition

oai_token-act-pair · gemini-2.0-flash

occurrences of the word "straight"

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

say straight

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

 resourceCulture

-1.01

 ModelExpression

-0.79

 disambiguazione

-0.78

reportWebVitals

-0.73

NameInMap

-0.72

 faſt

-0.71

 estekak

-0.70

 DBNull

-0.70

dataclass

-0.69

 <<<<<<<<<<<<<<

-0.68

POSITIVE LOGITS

 straight

0.56

 Straight

0.48

straight

0.47

Straight

0.46

BDD

0.43

Mud

0.42

водит

0.41

водить

0.39

 baie

0.39

Mul

0.39

Activations Density 1.337%

statistics related to a competition

occurrences of the word "straight"

say straight

No Comments

No Known Activations