INDEX

Explanations

scientific terms and concepts related to laboratory protocols and experiments

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

rå

-0.56

]--;

-0.53

 "','

-0.51

mid

-0.50

iotto

-0.48

burnt

-0.47

Mit

-0.47

ardia

-0.47

Mid

-0.46

uper

-0.45

POSITIVE LOGITS

 AssemblyTitle

0.79

 overnight

0.78

 <<<<<<<<<<<<<<

0.72

 BorderRadius

0.72

بوابة

0.69

rrggbb

0.68

TargetException

0.66

 estekak

0.65

 AttributeSet

0.65

omitempty

0.62

Activations Density 0.672%

scientific terms and concepts related to laboratory protocols and experiments

No Comments

No Known Activations