INDEX

Explanations

references to newness or updates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/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.19.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

popd

-0.48

รก

-0.47

 averaged

-0.46

 Coulter

-0.45

ʖ

-0.44

DebuggerNonUser

-0.44

choss

-0.44

 Bouchard

-0.44

haltet

-0.44

と思ったら

-0.43

POSITIVE LOGITS

 newOwner

0.78

Carriera

0.75

 تضيفلها

0.74

">—

0.71

 Italijanski

0.69

kháu

0.67

WriteTagHelper

0.66

تفصیلات

0.65

ंदीखरीदारी

0.63

 onCreateView

0.63

Activations Density 0.068%

references to newness or updates

No Comments

No Known Activations