INDEX

Explanations

references to indices in data structures or programming contexts

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

tshell

-0.67

Fm

-0.67

 Crot

-0.65

Искәрмәләр

-0.64

asymp

-0.63

SUNG

-0.63

 Alamofire

-0.62

MEP

-0.62

 longtemps

-0.61

 Santana

-0.61

POSITIVE LOGITS

 INDEX

1.42

 getIndex

1.41

 index

1.29

INDEX

1.28

 indices

1.28

 Index

1.26

 indexes

1.26

indexes

1.19

 Indices

1.18

 Indexes

1.18

Activations Density 0.126%

references to indices in data structures or programming contexts

No Comments

No Known Activations