INDEX

Explanations

terms and concepts related to legal cases and processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

:✨

-0.54

EDEFAULT

-0.47

دي

-0.46

catus

-0.45

tapan

-0.45

vited

-0.43

 déclar

-0.42

 høy

-0.42

Declar

-0.42

 ménages

-0.41

POSITIVE LOGITS

发表于

0.75

 surla

0.67

Races

0.66

 BoxDecoration

0.66

الدراسه

0.64

 وتسجيلات

0.64

ValueStyle

0.63

 nahilalakip

0.62

Trama

0.62

middels

0.61

Activations Density 0.898%

terms and concepts related to legal cases and processes

No Comments

No Known Activations