INDEX

Explanations

references and citations related to legal or investigative contexts

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

melidir

-0.54

 event

-0.52

 intra

-0.49

 nonUne

-0.48

oul

-0.47

 unit

-0.47

int

-0.47

-0.46

 special

-0.46

 call

-0.46

POSITIVE LOGITS

ⓧ

0.80

+#+

0.79

mybatisplus

0.79

0.75

 AssemblyCompany

0.74

sidemargin

0.73

ReusableCell

0.72

bootstrapcdn

0.70

NamedQueries

0.70

URLException

0.69

Activations Density 0.181%

references and citations related to legal or investigative contexts

No Comments

No Known Activations