INDEX

Explanations

comparisons involving numerical values

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

出版年

-0.58

 calendriers

-0.54

 estekak

-0.52

 surla

-0.50

verwijspagina

-0.49

GTCX

-0.49

fjspx

-0.48

Vidite

-0.47

 resourceCulture

-0.47

idł

-0.47

POSITIVE LOGITS

gt

1.47

lt

1.03

gt

0.97

GT

0.96

GT

0.77

Gt

0.73

lt

0.70

LT

0.69

Gt

0.66

LT

0.63

Activations Density 0.118%

comparisons involving numerical values

No Comments

No Known Activations