INDEX

Explanations

references to studies or reports, particularly those noting observations and findings

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

pms

-0.52

farwyddwr

-0.50

————————————

-0.49

 extérieures

-0.49

uestamente

-0.48

SHR

-0.48

 Folge

-0.47

ública

-0.47

 meals

-0.46

SHR

-0.45

POSITIVE LOGITS

])));

0.60

Geografi

0.59

 Superhost

0.58

 mxArray

0.55

yfik

0.55

gatsby

0.55

WithIOException

0.54

</caption>

0.54

OrBuilder

0.54

 ujednoznacz

0.54

Activations Density 0.765%

references to studies or reports, particularly those noting observations and findings

No Comments

No Known Activations