INDEX

Explanations

references to generalities and broad concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.34.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 algunos

-0.61

 algunas

-0.60

 many

-0.60

featureID

-0.59

 многих

-0.55

 some

-0.54

 algumas

-0.53

algunos

-0.53

 некоторые

-0.52

 некоторых

-0.52

POSITIVE LOGITS

 whatsoever

1.14

 imaginable

0.98

 ANYTHING

0.96

 anywhere

0.95

 anything

0.90

anything

0.88

 apapun

0.83

有任何

0.83

anywhere

0.82

 conceivable

0.81

Activations Density 0.442%

references to generalities and broad concepts

No Comments

No Known Activations