INDEX

Explanations

references to the effects of various treatments or conditions

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

 Dumas

-0.94

Bissau

-0.83

craper

-0.72

 Cunningham

-0.70

مصادر

-0.68

edicated

-0.67

تفصیلات

-0.66

estinal

-0.65

 inappropriés

-0.64

 Golem

-0.63

POSITIVE LOGITS

 effects

1.54

 Effects

1.45

Effects

1.42

 effect

1.38

effects

1.37

 Effect

1.32

Effect

1.28

 EFFECTS

1.27

effect

1.27

 EFFECT

1.22

Activations Density 0.205%

references to the effects of various treatments or conditions

No Comments

No Known Activations