INDEX

Explanations

metrics and results related to experimental assays

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 utom

-0.48

)("

-0.47

Архівовано

-0.46

')}}">

-0.45

levis

-0.45

jspx

-0.44

essentiel

-0.44

ด์

-0.44

 처리

-0.44

Outer

-0.43

POSITIVE LOGITS

 ویکی‌پدی

0.74

 الرياضيه

0.73

ConstraintMaker

0.67

انيف

0.65

styleType

0.62

Cordialement

0.59

 wireType

0.58

 beginnetje

0.57

ReusableCell

0.57

ISupport

0.57

Activations Density 0.895%

metrics and results related to experimental assays

No Comments

No Known Activations