INDEX

Explanations

technical terms and specific identifiers related to programming and scientific processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

VIAF

-0.69

isholm

-0.56

 reflects

-0.53

спонд

-0.52

 reflect

-0.51

 reflected

-0.51

ENEFITS

-0.50

TEMPO

-0.49

exus

-0.49

înes

-0.49

POSITIVE LOGITS

+#+#

0.74

titleMargin

0.73

+#+

0.66

évaluateur

0.65

 earthquake

0.64

 Wikispecies

0.61

ंदीखरीदारी

0.61

NamedQueries

0.60

burst

0.59

تفصیلات

0.58

Activations Density 2.042%

technical terms and specific identifiers related to programming and scientific processes

No Comments

No Known Activations