INDEX

Explanations

references to technical functions and roles within a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 ब्रेकडाउन

-0.59

GIVEREF

-0.52

UserScript

-0.50

 متعلقه

-0.48

новниш

-0.48

 propOrder

-0.48

 cosme

-0.47

 EconPapers

-0.47

 resourceCulture

-0.46

delwed

-0.45

POSITIVE LOGITS

 betweenstory

0.46

 valsty

0.40

 idé

0.36

 IBOutlet

0.36

Климат

0.35

ilija

0.34

⎞

0.34

 Malone

0.33

 aidant

0.33

 informée

0.33

Activations Density 0.790%

references to technical functions and roles within a document

No Comments

No Known Activations