INDEX

Explanations

questions and discussions related to programming and data structures in Python

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ValueStyle

-0.67

openConnection

-0.66

 vives

-0.54

 comarca

-0.53

formik

-0.50

 wenden

-0.50

 šal

-0.49

 fallu

-0.47

 positron

-0.47

 ouvertes

-0.46

POSITIVE LOGITS

 ProtoMessage

0.76

NameInMap

0.71

'])){

0.67

WireFormatLite

0.67

expandindo

0.65

principalColumn

0.64

///</

0.60

";

0.59

addCriterion

0.58

Rüyada

0.58

Activations Density 0.479%

questions and discussions related to programming and data structures in Python

No Comments

No Known Activations