INDEX

Explanations

programming constructs and attributes related to data models

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

onAttach

-0.57

BufferException

-0.57

 linkovi

-0.56

IndentedString

-0.54

 resourceCulture

-0.54

InjectAttribute

-0.51

Personendaten

-0.51

RotationOrder

-0.49

principalTable

-0.48

invokeLater

-0.47

POSITIVE LOGITS

皲

0.39

 parís

0.38

 bruto

0.36

一丝

0.35

 info

0.34

 information

0.33

ptures

0.33

 IntelliJ

0.33

 Farrell

0.32

 Gustaf

0.32

Activations Density 0.058%

programming constructs and attributes related to data models

No Comments

No Known Activations