INDEX

Explanations

class and method definitions in code

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

ollectionView

-0.57

 Fuerzas

-0.56

fandom

-0.56

quiel

-0.54

omethane

-0.53

WireFormatLite

-0.51

mogat

-0.49

 Pilate

-0.49

 Branco

-0.49

 inseparable

-0.48

POSITIVE LOGITS

AddTagHelper

0.90

 communiquez

0.66

featureID

0.61

parsedMessage

0.57

ArgsConstructor

0.56

 '\\;'

0.55

ImageContext

0.54

contentLoaded

0.52

 بيها

0.52

 Normdatei

0.51

Activations Density 0.377%

class and method definitions in code

No Comments

No Known Activations