INDEX

Explanations

legal terms and discussions related to search warrants and law enforcement actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 propOrder

-0.74

ArgsConstructor

-0.69

 AssemblyCulture

-0.69

 noDo

-0.68

 &___

-0.65

 upvote

-0.64

AutoField

-0.61

utnik

-0.59

ConstraintMaker

-0.59

󠁣

-0.59

POSITIVE LOGITS

 arrest

1.15

 search

1.12

 searches

1.05

 arrests

1.04

 searched

0.96

 arrested

0.94

 raids

0.94

 warrant

0.94

 Searches

0.94

 raid

0.93

Activations Density 0.532%

legal terms and discussions related to search warrants and law enforcement actions

No Comments

No Known Activations