INDEX

Explanations

programming-related keywords and function/method definitions

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

 /\.(

-0.71

InputBorder

-0.61

XmlEnum

-0.60

postmedia

-0.59

oredCriteria

-0.56

addCriterion

-0.56

aughter

-0.55

PathVariable

-0.54

 càng

-0.52

requestCode

-0.51

POSITIVE LOGITS

 dataSnapshot

0.63

 aVar

0.62

 iVar

0.58

 MonoBehaviour

0.57

RegressionTest

0.55

PyExc

0.51

îtra

0.51

 bArr

0.50

zzlies

0.49

الحياه

0.47

Activations Density 0.244%

programming-related keywords and function/method definitions

No Comments

No Known Activations