INDEX

Explanations

mentions of kits or packaged products

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

 Rosen

-0.54

AnimationsModule

-0.53

 Mullen

-0.53

 Rosenberg

-0.52

 pinulongan

-0.50

 Hough

-0.50

 Browne

-0.50

Coordenadas

-0.48

''

-0.47

 Corcoran

-0.46

POSITIVE LOGITS

kit

0.98

Kit

0.98

Kit

0.98

Kits

0.94

 Kits

0.93

KIT

0.93

kit

0.92

 kits

0.86

KIT

0.82

kits

0.80

Activations Density 0.008%

mentions of kits or packaged products

No Comments

No Known Activations