INDEX

Explanations

legal terminology related to acts and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 myſelf

-1.26

 itſelf

-1.16

 themſelves

-1.05

\{\\

-1.04

 pleaſure

-1.04

 himſelf

-1.03

ſelves

-0.98

Efq

-0.96

 Monfieur

-0.94

 ſeveral

-0.94

POSITIVE LOGITS

Act

1.17

 statute

0.96

 statue

0.91

Act

0.84

 statues

0.80

 acts

0.77

 rule

0.76

act

0.76

 Acts

0.75

 legislation

0.73

Activations Density 0.156%

legal terminology related to acts and regulations

No Comments

No Known Activations