INDEX

Explanations

code-related references and error messages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

Portale

-1.03

 Theſe

-0.83

 myſelf

-0.83

 whoſe

-0.83

DeleteBehavior

-0.80

 itſelf

-0.80

 uſe

-0.78

 uſed

-0.77

 feroit

-0.77

 étoit

-0.75

POSITIVE LOGITS

CJK

1.30

0.57

BASEPATH

0.56

 оригіналу

0.56

 arşivlendi

0.53

 constat

0.53

存于互联网档案馆

0.53

0.52

ApiException

0.52

heb

0.51

Activations Density 0.097%

code-related references and error messages

No Comments

No Known Activations