INDEX

Explanations

terms related to licensing and software distribution

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

LookAnd

-1.17

Tikang

-1.10

IsContent

-1.04

 Biôgrafia

-1.04

GEBURTSDATUM

-1.02

principalTable

-1.02

 ProtoMessage

-1.01

AsUp

-1.00

 Italijanski

-0.99

 ErrIntOverflow

-0.99

POSITIVE LOGITS

</strong>

0.70

0.66

0.55

0.54

0.51

0.49

</em>

0.49

0.48

“

0.47

</h2>

0.46

Activations Density 0.196%

terms related to licensing and software distribution

No Comments

No Known Activations