INDEX

Explanations

statements indicating discoveries or findings supported by data

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

 للمعارف

-0.68

 Wicidata

-0.53

⟬

-0.53

nachron

-0.52

sfw

-0.51

loaf

-0.51

ebenarnya

-0.51

archiviato

-0.50

☸

-0.50

CWE

-0.50

POSITIVE LOGITS

thâu

0.58

)}_

0.56

 PopupWindow

0.55

xaml

0.54

 SearchView

0.53

}));

0.52

 AssemblyVersion

0.51

"]]

0.51

 setuptools

0.51

'{@

0.50

Activations Density 0.487%

statements indicating discoveries or findings supported by data

No Comments

No Known Activations