INDEX

Explanations

technical terms and identifiers related to programming and system processes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

+#+#

-0.80

 Infórmanos

-0.72

 liệu

-0.68

Autoritní

-0.66

ifolium

-0.63

 propOrder

-0.62

fjspx

-0.62

SourceChecksum

-0.61

StoryboardSegue

-0.61

̣n

-0.58

POSITIVE LOGITS

 Мексичка

0.65

 تضيفلها

0.49

 '\\;'

0.47

bkz

0.46

issippi

0.46

engelsk

0.45

acular

0.42

PyExc

0.42

naby

0.42

Сайт

0.41

Activations Density 2.396%

technical terms and identifiers related to programming and system processes

No Comments

No Known Activations