INDEX

Explanations

terms related to interaction, particularly in the context of medical or scientific discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

تفصیلات

-0.69

 للمعارف

-0.59

webElementXpaths

-0.59

 ExecuteAsync

-0.58

dhury

-0.58

 transfieras

-0.56

Przypisy

-0.56

photobucket

-0.56

arbox

-0.54

Coroutine

-0.54

POSITIVE LOGITS

 Piero

0.62

 flyknit

0.59

 Pivot

0.59

 myſelf

0.59

jupiter

0.58

unhofer

0.58

 milan

0.58

 bienvenue

0.57

 EconPapers

0.56

 Inters

0.56

Activations Density 0.219%

terms related to interaction, particularly in the context of medical or scientific discussions

No Comments

No Known Activations