INDEX

Explanations

indicators of technical specifications or features in software contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 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

NUMX

-0.71

—

-0.68

—

-0.66

mandu

-0.62

uleiro

-0.62

 Paglinawan

-0.60

 שוליים

-0.59

Πηγές

-0.58

TargetException

-0.58

omaterial

-0.58

POSITIVE LOGITS

[toxicity=0]

0.72

↵

0.61

0.60

*/

0.59

</b>

0.57

0.56

0.54

German

0.54

English

0.53

French

0.53

Activations Density 0.583%

indicators of technical specifications or features in software contexts

No Comments

No Known Activations