INDEX

Explanations

terms related to legal procedures and requirements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Efq

-1.21

 ―――――

-1.19

 myſelf

-1.17

 itſelf

-1.16

$_"

-1.14

 Theſe

-1.07

 Jefus

-1.06

 ་་

-1.04

ſelves

-1.02

 Diſ

-1.02

POSITIVE LOGITS

 question

0.68

 hukum

0.64

<eos>

0.58

Can

0.58

0.54

can

0.53

Cor

0.52

Question

0.51

0.50

law

0.49

Activations Density 0.981%

terms related to legal procedures and requirements

No Comments

No Known Activations