INDEX

Explanations

terms related to intervention and interference in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Parcelize

-0.58

 planta

-0.56

djangoproject

-0.56

 joaat

-0.55

 commerciali

-0.54

 essa

-0.54

processable

-0.54

 Reece

-0.54

 Jacobson

-0.54

 speciali

-0.53

POSITIVE LOGITS

 intervene

1.80

 intervened

1.77

 intervention

1.74

Intervention

1.65

 Intervention

1.63

intervention

1.61

intervento

1.59

 interven

1.56

 intervenir

1.45

Interventions

1.45

Activations Density 0.208%

terms related to intervention and interference in various contexts

No Comments

No Known Activations