INDEX

Explanations

numerical representations or mathematical expressions related to various computes or calculations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

↵↵

-0.75

ness

-0.74

er

-0.74

<sup>

-0.73

an

-0.71

ers

-0.70

ism

-0.68

ше

-0.66

ings

-0.65

en

-0.64

POSITIVE LOGITS

 }}$}

1.46

]")]

1.45

"}

1.41

"]}

1.40

']}

1.32

'}

1.30

")}

1.28

"}

1.22

";}

1.18

).}

1.16

Activations Density 0.311%

numerical representations or mathematical expressions related to various computes or calculations

No Comments

No Known Activations