INDEX

Explanations

questions and exclamatory phrases

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

Controllo

-0.48

adjoint

-0.47

pla

-0.47

Ala

-0.46

 Majefty

-0.44

ícone

-0.44

entic

-0.44

 houſe

-0.44

 Bren

-0.43

Eſ

-0.43

POSITIVE LOGITS

 LUMP

0.90

XmlAccessType

0.81

withIdentifier

0.77

帖最后由

0.74

 سكانية

0.74

#+#

0.73

 rospy

0.72

ngdoc

0.72



0.72

下载附件

0.71

Activations Density 0.094%

questions and exclamatory phrases

No Comments

No Known Activations