INDEX

Explanations

mentions of performance-related contexts in various settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

-0.68

de

-0.63

vor

-0.57

-0.56

der

-0.56

-0.55

il

-0.54

 solid

-0.53

POSITIVE LOGITS

 Diſ

1.47

 Anſ

1.34

 ſtate

1.29

 Reſ

1.28

Eſ

1.27

 myſelf

1.26

 Jefus

1.20

 itſelf

1.20

 ſeveral

1.19

 Perſ

1.17

Activations Density 0.171%

mentions of performance-related contexts in various settings

No Comments

No Known Activations