INDEX

Explanations

numerical comparisons related to performance and history

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

splash

-0.44

hit

-0.41

Footnotes

-0.40

sp

-0.40

arxiv

-0.40

 link

-0.39

________________

-0.39

makeText

-0.39

-0.38

its

-0.38

POSITIVE LOGITS

Personensuche

0.83

✭✭

0.79

 Normdatei

0.75

 FetchType

0.75

SourceChecksum

0.73

IUrlHelper

0.70

oredCriteria

0.70

 ddelweddau

0.69

 nahilalakip

0.68

webElementXpaths

0.68

Activations Density 0.093%

numerical comparisons related to performance and history

No Comments

No Known Activations