INDEX

Explanations

references to frameworks or packages related to programming, specifically in the context of code structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

verwijspagina

-0.74

 ujednoznacz

-0.59

RegressionTest

-0.59

webElementGuid

-0.58

localctx

-0.54

TypedDataSet

-0.52

 Offisielt

-0.52

ApiModel

-0.51

RegistryLite

-0.51

 CreateTagHelper

-0.50

POSITIVE LOGITS

 sienta

0.41

 firme

0.38

Jeografia

0.38

四人

0.37

 withRouter

0.36

autogui

0.36

wahlen

0.35

感覚

0.34

givings

0.34

awtextra

0.34

Activations Density 0.000%

references to frameworks or packages related to programming, specifically in the context of code structure

No Comments

No Known Activations