INDEX

Explanations

terms related to causal relationships and effects

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

"cause"

np_acts-logits-general · gemini-2.0-flash

cause and effect

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

verständlich

-0.74

EndInit

-0.70

 EconPapers

-0.69

 Administrativna

-0.68

}{*}{}

-0.67

Autoritní

-0.67

 שוליים

-0.64

compromised

-0.64

AsUp

-0.63

🏻

-0.63

POSITIVE LOGITS

 havoc

0.83

 célèbres

0.78

 harm

0.75

 damage

0.69

 célèbre

0.67

 celebre

0.59

 efecto

0.59

 efeito

0.57

 kysy

0.57

effect

0.56

Activations Density 0.098%

terms related to causal relationships and effects

"cause"

cause and effect

No Comments

No Known Activations