INDEX

Explanations

numbers and their relationships in a dataset

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

gregor

-0.55

-0.52

amship

-0.52

rinol

-0.50

albero

-0.50

 ettiği

-0.49

Odkazy

-0.48

 بلغ

-0.48

yordu

-0.46

asserole

-0.46

POSITIVE LOGITS

GEBURTSDATUM

0.79

ViewFeatures

0.78

IndentedString

0.69

IsMutable

0.69

addCriterion

0.68

CodedInputStream

0.68

ItemBackground

0.68

saraba

0.67

 Numerade

0.66

SharedCtor

0.65

Activations Density 0.312%

numbers and their relationships in a dataset

No Comments

No Known Activations