INDEX

Explanations

punctuation marks and end-of-sentence indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

onAttach

-0.73

contentLoaded

-0.69

 NUKAT

-0.67

 विश्वसनीयता

-0.66

enumii

-0.66

 صوتيه

-0.66

 للاسماء

-0.66

يكب

-0.66

Aholisi

-0.65

 EconPapers

-0.64

POSITIVE LOGITS

0.56

مصادر

0.55

 }^{[

0.52

brus

0.51

kus

0.50

Примечания

0.49

ന്

0.48

Wil

0.48

DispatchToProps

0.48

 Their

0.47

Activations Density 0.812%

punctuation marks and end-of-sentence indicators

No Comments

No Known Activations