INDEX

Explanations

references to self-inclusion and related terms in discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.34.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

oplayer

-0.32

 AssemblyCompany

-0.29

berus

-0.29

jv

-0.28

PROLOG

-0.28

 [][]

-0.27

 ditem

-0.27

 MenuView

-0.27

ApiOperation

-0.26

initializeApp

-0.26

POSITIVE LOGITS

 included

3.22

included

2.88

 inclusion

2.80

 Included

2.66

Included

2.55

 INCLUDED

2.47

inclusion

2.36

 Inclusion

2.33

 inclus

2.27

Inclusion

2.19

Activations Density 1.151%

references to self-inclusion and related terms in discussions

No Comments

No Known Activations

references to self-inclusion and related terms in discussions

No Comments

No Known Activations