INDEX

Explanations

references to the concept of "wholeness" or completeness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 Réponses

-0.72

'",

-0.70

'";

-0.67

ic

-0.65

 limestones

-0.64

 DataTypes

-0.63

 Parkinson

-0.61

Cuisine

-0.59

Ellis

-0.59

 nakalista

-0.59

POSITIVE LOGITS

 entire

1.74

 whole

1.69

whole

1.68

Whole

1.62

 WHOLE

1.61

 Whole

1.58

 Entire

1.46

entire

1.42

 ENTIRE

1.41

Entire

1.32

Activations Density 0.046%

references to the concept of "wholeness" or completeness

No Comments

No Known Activations