INDEX

Explanations

terms and phrases related to measurements and performance evaluations in technology or medical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Tikang

-0.71

 Shakspeare

-0.50

｀*)

-0.50

 NDEBUG

-0.50

 tartalomajánló

-0.48

 Egli

-0.47

 cabo

-0.47

 Southwestern

-0.46

 Theſe

-0.46

Suf

-0.46

POSITIVE LOGITS

jstor

0.64

近年

0.63

ymce

0.59

 AssemblyTitle

0.56

endpush

0.54

 recent

0.52

近年来

0.51

hoeddwyd

0.51

最近

0.51

prits

0.51

Activations Density 1.219%

terms and phrases related to measurements and performance evaluations in technology or medical contexts

No Comments

No Known Activations