INDEX

Explanations

text related to code elements, such as classes and properties in programming languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

SpringBootTest

-0.88

 BoxFit

-0.82

 >=",

-0.78

,:,

-0.74

}{*}{}

-0.74

 '\\;'

-0.73

 onOptions

-0.71

InputBorder

-0.70

 HasFactory

-0.69

 jLabel

-0.68

POSITIVE LOGITS

 énergé

0.60

dotenv

0.58

cipar

0.55

 PropTypes

0.51

 poil

0.51

 lisse

0.51

 çöz

0.49

 aeruginosa

0.48

 fraî

0.48

 ailleurs

0.48

Activations Density 6.735%

text related to code elements, such as classes and properties in programming languages

No Comments

No Known Activations