INDEX

Explanations

phrases indicating the start of a new section or unit of text

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

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

-0.75

таратура

-0.70

+:+

-0.53

transQ

-0.52

Enllaces

-0.51

 surla

-0.51

 disambiguazione

-0.48

脚注の使い方

-0.47

eaways

-0.46

richTextPanel

-0.43

POSITIVE LOGITS

STORY

0.41

 poffible

0.41

UnsafeEnabled

0.41

GF

0.40

 setCurrent

0.38

 CGFloat

0.38

 PopupWindow

0.38

 raiſ

0.37

story

0.37

Gov

0.37

Activations Density 0.072%

phrases indicating the start of a new section or unit of text

No Comments

No Known Activations