INDEX

Explanations

structured phrases related to investigations and claims

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

webElementXpaths

-0.59

 LUMI

-0.57

FromArgb

-0.56

OPSIS

-0.56

outSlope

-0.55

 通販

-0.55

Efq

-0.55

?>/

-0.54

 calendriers

-0.52

<bos>

-0.52

POSITIVE LOGITS

 disambiguazione

0.63

verwijspagina

0.58

 autorytatywna

0.57

ⓘ

0.53

 EconPapers

0.53

Autoritní

0.52

abetes

0.52

dafx

0.52

 externes

0.51

migrationBuilder

0.49

Activations Density 0.004%

structured phrases related to investigations and claims

No Comments

No Known Activations