INDEX

Explanations

questions and uncertainties regarding specific details or subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

archiviato

-0.63

]")]

-0.56

 regioni

-0.53

 coloridas

-0.51

 externi

-0.50

piecze

-0.49

 rosse

-0.49

거

-0.48

DoubleQuotes

-0.47

 fieldNum

-0.46

POSITIVE LOGITS

depends

0.76

 depends

0.76

 unclear

0.64

 details

0.64

 depending

0.63

 exact

0.62

depending

0.61

 Depends

0.60

詳細は

0.60

icago

0.59

Activations Density 0.393%

questions and uncertainties regarding specific details or subjects

No Comments

No Known Activations