INDEX

Explanations

definitions and classifications related to legal terms and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

 يتيمه

-0.54

انجليز

-0.51

 menangani

-0.47

umd

-0.47

mba

-0.46

 Чтобы

-0.45

imageshack

-0.44

Mar

-0.43

gadier

-0.43

Mar

-0.42

POSITIVE LOGITS

 meaning

0.69

 definition

0.69

 itſelf

0.66

 means

0.66

 defined

0.65

MEAN

0.64

 Meaning

0.61

 Theſe

0.60

 Defined

0.59

Rüyada

0.58

Activations Density 0.405%

definitions and classifications related to legal terms and conditions

No Comments

No Known Activations