INDEX

Explanations

scientific terminology related to measurements and biological constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 purpoſe

-0.86

 ſmall

-0.83

TypedDataSet

-0.81

 arşivlendi

-0.79

 AssemblyTitle

-0.79

 houſe

-0.79

contentLoaded

-0.78

 myſelf

-0.78

 itſelf

-0.76

 useAppContext

-0.76

POSITIVE LOGITS

0.41

rev

0.41

‚

0.38

 sing

0.38

Mot

0.38

ränkt

0.37

 Chicken

0.37

adaptiveStyles

0.37

aus

0.36

Activations Density 0.642%

scientific terminology related to measurements and biological constructs

No Comments

No Known Activations