INDEX

Explanations

legal terminology and phrases associated with court cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 snippetHide

-0.68

+#+#

-0.60

ductory

-0.54

 ModelExpression

-0.53

 createSlice

-0.53

 verkle

-0.49

&_

-0.49

 status

-0.48

PHA

-0.47

 bals

-0.47

POSITIVE LOGITS

 defendant

1.59

 defendants

1.51

 plaintiff

1.33

 respondent

1.24

 Defendant

1.23

 plaintiffs

1.21

 respondents

1.20

 Defendants

1.15

Defendant

1.14

defendant

1.12

Activations Density 1.489%

legal terminology and phrases associated with court cases

No Comments

No Known Activations