INDEX

Explanations

names and descriptors related to individuals or characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

:✨

-0.77

 propOrder

-0.76

 pinulongan

-0.74

XMLSchema

-0.71

 متعلقه

-0.70

]--;

-0.67

 ISNI

-0.67

 simplifié

-0.66

mybatisplus

-0.65

verwijspagina

-0.65

POSITIVE LOGITS

الصفحه

0.50

 OnEnable

0.44

tım

0.43

del

0.43

 domestiques

0.43

 concernés

0.42

kuš

0.42

 Kessler

0.42

 Оно

0.41

TestingModule

0.41

Activations Density 0.712%

names and descriptors related to individuals or characters

No Comments

No Known Activations