INDEX

Explanations

terms related to universality or collective experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

//

-0.60

Bauer

-0.57

ه‌اند

-0.56

ässä

-0.55

zt

-0.54

йом

-0.53

ktır

-0.53

DaoImpl

-0.52

Cone

-0.52

POSITIVE LOGITS

every

1.64

 every

1.61

 EVERY

1.60

EVERY

1.59

 Every

1.53

Every

1.46

 Ogni

1.21

 Everywhere

1.11

 Jede

1.07

 Jedes

1.07

Activations Density 0.049%

terms related to universality or collective experiences

No Comments

No Known Activations