INDEX

Explanations

phrases indicating abundance or quantity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

CrossRef

-0.98

 Penrose

-0.82

setVerticalGroup

-0.79

 Schäfer

-0.78

etzten

-0.77

CardHeader

-0.76

Suz

-0.75

⌉

-0.74

/*---

-0.74

δες

-0.73

POSITIVE LOGITS

lot

1.94

 lots

1.54

Lot

1.46

Lot

1.41

LOT

1.39

 LOTS

1.37

Lots

1.36

 alot

1.34

 Lots

1.34

lots

1.17

Activations Density 0.058%

phrases indicating abundance or quantity

No Comments

No Known Activations