INDEX

Explanations

references to time periods or moments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 оригіналу

-0.56

HttpPut

-0.54

awtextra

-0.52

 parseFrom

-0.52

anz

-0.51

DispatchToProps

-0.51

AsStream

-0.51

SourceChecksum

-0.50

Mal

-0.49

calyp

-0.48

POSITIVE LOGITS

 auffi

0.80

 Himo

0.70

Obrázky

0.69

 Exacts

0.64

 ujednoznacz

0.64

WaitGroup

0.63

 jahre

0.63

 reaſon

0.61

 years

0.61

 YEARS

0.60

Activations Density 0.219%

references to time periods or moments

No Comments

No Known Activations