INDEX

Explanations

legal terminology and references to allegations or contentions in a legal context

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

存于互联网档案馆

-0.59

colgroup

-0.57

!("{

-0.53

amentals

-0.52

 아이콘

-0.52

плуата

-0.52

 Futuro

-0.51

balt

-0.51

 ?>">

-0.51

 Future

-0.51

POSITIVE LOGITS

 claims

1.87

 claim

1.78

 Claims

1.64

 Claim

1.62

 claimed

1.60

 CLAIM

1.53

 claiming

1.51

Claim

1.51

 CLAIMS

1.51

claims

1.48

Activations Density 0.501%

legal terminology and references to allegations or contentions in a legal context

No Comments

No Known Activations