INDEX

Explanations

commands and prompts related to user interactions and navigation

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 propOrder

-0.95

 незавершена

-0.89

GraphicsUnit

-0.89

 Italijani

-0.81

LookAnd

-0.79

djangoproject

-0.75

AndroidJUnit

-0.73

superuser

-0.73

 JpaRepository

-0.73

Efq

-0.72

POSITIVE LOGITS

 full

0.52

 Full

0.51

>>

0.50

 Datenschutzer

0.48

 EconPapers

0.48

Full

0.47

<eos>

0.46

全文

0.46

scar

0.42

common

0.41

Activations Density 0.400%

commands and prompts related to user interactions and navigation

No Known Activations