INDEX

Explanations

terms associated with legal concepts and professionals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

MemoryWarning

-0.88

VIAF

-0.80

RenderAtEndOf

-0.75

 CreateTagHelper

-0.74

InjectAttribute

-0.69

 mostrarse

-0.66

 enriquec

-0.66

 تضيفلها

-0.64

prägt

-0.63

帖最后由

-0.62

POSITIVE LOGITS

 legal

4.62

 Legal

4.18

Legal

4.12

legal

4.05

 LEGAL

3.81

LEGAL

3.38

 legales

2.84

 legally

2.77

 legale

2.76

 légal

2.46

Activations Density 0.092%

terms associated with legal concepts and professionals

No Comments

No Known Activations