INDEX

Explanations

specific biochemical or medical terms and parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 doInBackground

-0.91

 Réponses

-0.88

 Humphries

-0.82

—

-0.81

PageContext

-0.81

جمعیت

-0.78

 estekak

-0.75

 BoxFit

-0.74

XmlAccessType

-0.74

lenmiş

-0.74

POSITIVE LOGITS

lllll

1.01

Jol

1.00

lll

0.95

llll

0.95

llllll

0.94

JL

0.92

lllllll

0.91

Kl

0.89

Zil

0.89

CUL

0.88

Activations Density 1.792%

specific biochemical or medical terms and parameters

No Comments

No Known Activations