INDEX

Explanations

programming and function-related terminology 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 @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

Portail

-0.63

expandindo

-0.58

 PopupWindow

-0.54

 ISNI

-0.52

CloseOperation

-0.47

ManyToMany

-0.47

 /\.(

-0.46

 الدولى

-0.46

Rohy

-0.46

AutoresizingMask

-0.46

POSITIVE LOGITS

BeanUtils

0.80

thenReturn

0.58

jsonwebtoken

0.57

inflate

0.56

lapsingToolbar

0.56

 mergeFrom

0.55

Incomplete

0.54

 copied

0.53

 AutoMapper

0.53

 model

0.53

Activations Density 0.134%

programming and function-related terminology in code

No Comments

No Known Activations