INDEX

Explanations

references to sequential events or instances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Theſe

-1.11

Efq

-1.01

 Shakspeare

-0.87

 Diſ

-0.87

 ―――――

-0.86

 myſelf

-0.85

 Perſ

-0.83

 itſelf

-0.82

 Winaray

-0.81

 Anſ

-0.81

POSITIVE LOGITS

 second

0.94

 Second

0.78

 SECOND

0.77

second

0.75

Second

0.71

II

0.70

第二次

0.69

 segunda

0.69

 ikinci

0.68

 deuxième

0.66

Activations Density 0.755%

references to sequential events or instances

No Comments

No Known Activations