INDEX

Explanations

technical terms related to programming and functionality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

достатки

-0.46

mær

-0.45

èges

-0.45

<tr>

-0.44

层

-0.43

러나

-0.42

visel

-0.41

lexus

-0.41

גן

-0.41

sanity

-0.41

POSITIVE LOGITS

AxisAlignment

0.83

RectangleBorder

0.81

 BoxFit

0.81

ContentAsync

0.79

\{\\

0.78

 estekak

0.75

 useHistory

0.74

ollectionView

0.74

 EconPapers

0.72

InstanceState

0.71

Activations Density 2.545%

technical terms related to programming and functionality

No Comments

No Known Activations