INDEX

Explanations

references to data structures, specifically lists and nested items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 disambiguazione

-0.60

 <>",

-0.55

SpringBootTest

-0.54

 &___

-0.49

NewUrlParser

-0.49

XmlAccessorType

-0.48

Elő

-0.47

uxxxx

-0.47

rrggbb

-0.47

Tikang

-0.46

POSITIVE LOGITS

 الحره

0.66

0.65

 propOrder

0.63

numerusform

0.56

WebElementEntity

0.54

 подраз

0.53

المكان

0.53

ereich

0.52

yntaxException

0.52

rechte

0.51

Activations Density 0.699%

references to data structures, specifically lists and nested items

No Comments

No Known Activations