INDEX

Explanations

references to a root structure or hierarchy in a data or programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

MIDDLEWARE

-0.83

 Chamb

-0.77

httphttps

-0.75

 fibrillation

-0.74

SDC

-0.74

żeli

-0.70

 influenza

-0.70

 Lari

-0.70

 carnival

-0.69

lcccc

-0.69

POSITIVE LOGITS

 ROOT

1.57

 Root

1.54

 Roots

1.50

 roots

1.49

 root

1.46

ROOT

1.42

Roots

1.38

roots

1.37

root

1.32

Root

1.32

Activations Density 0.061%

references to a root structure or hierarchy in a data or programming context

No Comments

No Known Activations