INDEX

Explanations

legal terminology related to criminal charges and convictions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

+#+#

-0.62

 noten

-0.60

Clik

-0.58

tvguidetime

-0.54

InputBorder

-0.54

ipy

-0.51

 виправивши

-0.51

ATIVO

-0.49

WithEmail

-0.49

wij

-0.49

POSITIVE LOGITS

 charges

0.67

 felony

0.65

 misdemeanor

0.64

Personendaten

0.63

 charged

0.62

msgTypes

0.56

 breach

0.56

 conspiracy

0.55

 charge

0.54

itonitis

0.53

Activations Density 0.491%

legal terminology related to criminal charges and convictions

No Comments

No Known Activations