INDEX

Explanations

calls to action related to reading or learning more about content

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Diweddarwch

-0.88

 propOrder

-0.83

 invokingState

-0.83

 tartalomajánló

-0.79

 nakalista

-0.76

NUMX

-0.76

 bezeichneter

-0.76

 CanadaChoose

-0.75

énario

-0.75

URLException

-0.73

POSITIVE LOGITS

 tež

0.55

 tartış

0.47

setCustom

0.45

Read

0.45

 veiligheid

0.42

ưng

0.42

Learn

0.41

робнее

0.41

完整

0.41

 more

0.41

Activations Density 0.129%

calls to action related to reading or learning more about content

No Comments

No Known Activations