INDEX

Explanations

references to scientific methodologies and classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 <<<<<<<<<<<<<<

-0.49

basicConfig

-0.47

">//

-0.47

ThroughAttribute

-0.46

enterOuterAlt

-0.46

rungsseite

-0.45

MigrationBuilder

-0.44

bootstrapcdn

-0.42

//

-0.42

GOTREF

-0.42

POSITIVE LOGITS

verifyException

0.41

mapbox

0.39

 merek

0.38

interact

0.37

 Administrativna

0.37

secta

0.36

さすが

0.35

 nacionalidad

0.35

spender

0.35

 interacting

0.35

Activations Density 0.879%

references to scientific methodologies and classifications

No Comments

No Known Activations