INDEX

Explanations

references to multiple instances or concepts of "triples."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 viewDidLoad

-0.71

AutoScale

-0.66

InjectAttribute

-0.65

permute

-0.63

 ostavi

-0.62

sejarah

-0.61

SerializedName

-0.59

setVerticalGroup

-0.59

-0.58

 Sarko

-0.58

POSITIVE LOGITS

де

0.69

 organs

0.63

 Wicidata

0.61



0.61

Niz

0.60

 kidneys

0.57

 smtplib

0.56

 httpClient

0.52

 Privacidade

0.50

FECTION

0.50

Activations Density 0.143%

references to multiple instances or concepts of "triples."

No Comments

No Known Activations