INDEX

Explanations

references to specific entities or categories related to media and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

MessageOf

-1.05

SharedDtor

-0.89

 estekak

-0.88

 ProtoMessage

-0.85

AddTagHelper

-0.83

 Италијани

-0.83

 للاسماء

-0.82

PyExc

-0.81

wpi

-0.81

UrlResolution

-0.80

POSITIVE LOGITS

™

0.54

orod

0.51

0.48

 GmbH

0.47

ú

0.46

tes

0.45

®

0.44

hin

0.43

 prese

0.43

LLC

0.43

Activations Density 1.247%

references to specific entities or categories related to media and data structures

No Comments

No Known Activations