INDEX

Explanations

references to quantitative data and parameters in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

ագրություններ

-0.52

DoubleQuotes

-0.52

ChildScrollView

-0.50

 entanto

-0.50

ắt

-0.46

Cyfeiriadau

-0.45

addPreferredGap

-0.44

IBar

-0.43

eradish

-0.42

 standardization

-0.42

POSITIVE LOGITS

<![

0.66

Kaieteur

0.65

存于互联网档案馆

0.60

hankelijk

0.57

 schließlich

0.57

“……”

0.57

 CanadaChoose

0.56

})$.

0.55

reportWebVitals

0.53

 crossorigin

0.53

Activations Density 0.437%

references to quantitative data and parameters in various contexts

No Comments

No Known Activations