INDEX

Explanations

specific technical terms and identifiers related to software and programming, especially in the context of APIs and libraries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

aarrggbb

-0.76

 estekak

-0.76

 архивлан

-0.76

AnchorStyles

-0.72

 CURLOPT

-0.71

")->

-0.70

makeText

-0.70

etheless

-0.63

PreferredItem

-0.62

 initComponents

-0.62

POSITIVE LOGITS

 family

0.62

 series

0.61

series

0.60

family

0.58

 geslacht

0.53

ideae

0.52

系列

0.51

 серии

0.51

yonel

0.50

 Series

0.49

Activations Density 0.635%

specific technical terms and identifiers related to software and programming, especially in the context of APIs and libraries

No Comments

No Known Activations