INDEX

Explanations

references to the act of changing or modifying something

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 layui

-0.76

ništvo

-0.73

PMailer

-0.69

цездатний

-0.68

mybatisplus

-0.66

öße

-0.64

ensement

-0.62

elang

-0.62

ardless

-0.61

はじめに

-0.61

POSITIVE LOGITS

tvguidetime

0.85

0.81

 nicio

0.80

Portail

0.75

Mep

0.73

">//

0.73

\{\\

0.70

 désol

0.69

[toxicity=0]

0.68

 }}"></

0.68

Activations Density 0.002%

references to the act of changing or modifying something

No Comments

No Known Activations