INDEX

Explanations

references to political figures and their actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 disambiguazione

-0.76

webElementXpaths

-0.76

ValueStyle

-0.71

ſſung

-0.67

iſchen

-0.64

rungsseite

-0.63

ſicht

-0.62

Autoritní

-0.61

tanleria

-0.60

KommentareTeilen

-0.59

POSITIVE LOGITS

 retired

0.35

 pergi

0.30

 Karten

0.30

 пен

0.29

Hir

0.28

命的

0.28

쓴

0.27

 longa

0.27

достатки

0.27

 grandchildren

0.26

Activations Density 0.220%

references to political figures and their actions

No Comments

No Known Activations