INDEX

Explanations

dates and numerical references in text

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

prefixer

-0.84

TagMode

-0.81

 myſelf

-0.74

 насељу

-0.72

\]

-0.71

 chi̍t

-0.71

)<=

-0.70

 كومونز

-0.69

IBOutlet

-0.69

 незавершена

-0.69

POSITIVE LOGITS

+#+

0.49

RNA

0.47

 also

0.45

 ioutil

0.45

rxjs

0.44

 QtCore

0.43

0.42

 OnInit

0.42

 trajets

0.41

lgica

0.41

Activations Density 0.154%

dates and numerical references in text

No Comments

No Known Activations