INDEX

Explanations

references to specific entities or important terms within a 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

ValueStyle

-0.66

ArgsConstructor

-0.62

AddTagHelper

-0.61

بوابة

-0.60

 ligiloj

-0.57

 متعلقه

-0.56

viewDidLoad

-0.53

fts

-0.49

 Pittman

-0.48

انجليز

-0.48

POSITIVE LOGITS

Ikus

0.50

 createState

0.48

mintaan

0.48

 audience

0.47

 Paglinawan

0.47

 QLabel

0.45

'__

0.45

 receptors

0.45

 потреби

0.45

 своими

0.44

Activations Density 1.106%

references to specific entities or important terms within a context

No Comments

No Known Activations