INDEX

Explanations

phrases related to enabling or facilitating actions and processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 vectorielles

-0.89

 avoient

-0.84

 auroit

-0.83

 définiti

-0.79

 feroit

-0.78

 réguli

-0.78

 étoient

-0.77

 présidenti

-0.76

 Monfieur

-0.76

 fédé

-0.76

POSITIVE LOGITS

 enable

0.93

 enables

0.87

 allow

0.87

 allows

0.80

 permit

0.78

 enabling

0.74

 enabled

0.69

 allowing

0.65

 envisage

0.62

 envision

0.61

Activations Density 0.158%

phrases related to enabling or facilitating actions and processes

No Comments

No Known Activations