INDEX

Explanations

technical jargon and terms specifically related to data analysis and manipulation

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

Reference identifiers or action verbs within technical/scientific documents, typically within citation formats, code comments, or document structure elements.

eleuther_acts_top20 · claude-3-7-sonnet-20250219 Triggered by @lu-christina

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

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

protoimpl

-0.42

endphp

-0.37

/*

-0.36

]=>

-0.35

 ProtoMessage

-0.34

 Roskov

-0.33

Personendaten

-0.32

flashdata

-0.32

">//

-0.31

ftagPool

-0.31

POSITIVE LOGITS

orghini

0.61

liosis

0.52

 Skiing

0.50

ollectionView

0.49

chieht

0.48

zaamheid

0.48

 farm

0.48

UTI

0.48



0.47

tershire

0.47

Activations Density 0.532%

technical jargon and terms specifically related to data analysis and manipulation

Reference identifiers or action verbs within technical/scientific documents, typically within citation formats, code comments, or document structure elements.

No Comments

No Known Activations