INDEX

Explanations

references to awards and honors associated with individuals

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

addContainerGap

-0.53

 surla

-0.52

miede

-0.52

 teaching

-0.50

 BEER

-0.50

тябрь

-0.48

 halo

-0.48

worten

-0.48

EnableWeb

-0.48

гинал

-0.47

POSITIVE LOGITS

FormTagHelper

0.75

::::::::

0.66

 AssemblyProduct

0.62

 propOrder

0.62

apnews

0.57

nodoc

0.57

 credere

0.57

 tranſ

0.57

новништво

0.56

 urgente

0.55

Activations Density 0.103%

references to awards and honors associated with individuals

No Comments

No Known Activations