INDEX

Explanations

references to electroencephalography and medical terminology related to treatments and studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

pen

-0.46

 radio

-0.46

bio

-0.44

sim

-0.44

大戦

-0.43

air

-0.43

=>$

-0.43

ジング

-0.42

 Lipp

-0.42

 nuclear

-0.41

POSITIVE LOGITS

PerformLayout

0.82

})()

0.75

tableFuture

0.74

 noqa

0.72

berdayakan

0.72

 estekak

0.71

 مرئيه

0.69

antaranya

0.69

 GetComponent

0.69

vedades

0.67

Activations Density 2.049%

references to electroencephalography and medical terminology related to treatments and studies

No Comments

No Known Activations