INDEX

Explanations

references to memorials, honors, and tributes in commemorating individuals or events

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

 Preferencias

-0.66

kheim

-0.63

ContentAsync

-0.58

__);

-0.55

vezet

-0.54

 Rhine

-0.54

ukseen

-0.54

CPD

-0.53

WillAppear

-0.52

 Мексичка

-0.52

POSITIVE LOGITS

InjectAttribute

0.58

 mémoire

0.56

 memories

0.53

 accomplishments

0.53

 minne

0.53

 commemorate

0.53

 memoria

0.51

 memory

0.50

 departed

0.50

memories

0.49

Activations Density 0.121%

references to memorials, honors, and tributes in commemorating individuals or events

No Comments

No Known Activations