INDEX

Explanations

numbers and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 nonatomic

-0.74

Према

-0.69

󠁢

-0.69

 ddelweddau

-0.68

 Italijani

-0.66

esgue

-0.65

cardia

-0.65

bolista

-0.64

iented

-0.62

BagConstraints

-0.62

POSITIVE LOGITS

BeginContext

0.66

=”

0.49

tagHelperRunner

0.46

MessageOf

0.43

 linkovi

0.42

StoreMessageInfo

0.41

Personendaten

0.41

 elég

0.40

ktır

0.40

pa

0.39

Activations Density 0.339%

numbers and symbols

No Comments

No Known Activations