INDEX

Explanations

specific names and identifiers related to authors, experiments, or technical components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

]=>

-0.41

MigrationBuilder

-0.40

Kib

-0.38

CIM

-0.38

kib

-0.37

HPLC

-0.36

cot

-0.35

tagHelperRunner

-0.34

readdir

-0.34

Искәрмәләр

-0.33

POSITIVE LOGITS

Personendaten

0.84

CloseOperation

0.55

 maternelle

0.54

 utafitiHapana

0.54

 hırka

0.51

esistenza

0.51

 disambiguazione

0.50

ніципалі

0.50

 الحره

0.50

GOTREF

0.50

Activations Density 1.228%

specific names and identifiers related to authors, experiments, or technical components

No Comments

No Known Activations