INDEX

Explanations

references to events, locations, or mathematical and technical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

missie

-0.49

offsetTop

-0.49

Erfahrung

-0.49

пиона

-0.49

AlreadyExists

-0.47

Revenir

-0.46

 embarazada

-0.46

rboles

-0.45

goire

-0.45

otrop

-0.44

POSITIVE LOGITS

 تضيفلها

0.78

WithIOException

0.77

 FUNERAL

0.77

 Funeral

0.76

ніципа

0.76



0.75

 funeral

0.75

 defaultstate

0.73

databinding

0.72

OGND

0.71

Activations Density 0.038%

references to events, locations, or mathematical and technical terms

No Comments

No Known Activations