INDEX

Explanations

connections and interactions between various entities and concepts

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

プーン

-0.71

й

-0.68

штей

-0.65

 fous

-0.63

 CommonModule

-0.60

TDC

-0.59

География

-0.59

zd

-0.58

 plomb

-0.57

POSITIVE LOGITS

 interactions

1.41

 interaction

1.34

 Interactions

1.30

Interactions

1.30

 Interaction

1.29

 Interact

1.29

 interact

1.27

interactions

1.26

interaction

1.22

Interaction

1.22

Activations Density 0.061%

connections and interactions between various entities and concepts

No Comments

No Known Activations