INDEX

Explanations

phrases requesting participation or action from interested parties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

InstrumentedTest

-0.68

 referenties

-0.67

Geplaatst

-0.67

 OFDb

-0.62

 שוליים

-0.61

BeginContext

-0.60

 EClass

-0.59

usalem

-0.56

setopt

-0.56

wahati

-0.55

POSITIVE LOGITS

adaptiveStyles

0.61

 yourself

0.58

yourself

0.55

 yourselves

0.55

 Applicability

0.54

出版年

0.51

 autorytatywna

0.51

 applicability

0.50

これを

0.50

Applicable

0.48

Activations Density 0.325%

phrases requesting participation or action from interested parties

No Comments

No Known Activations